Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    special characters and syntax patterns commonly used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text enclosed in parentheses/brackets with symbols and variables

    np_acts-logits-general · gemini-2.0-flash

    special characters followed by letters or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -1.01
    zkopf
    -0.68
    Referencias
    -0.67
    verständlich
    -0.66
    \]
    -0.65
     }^{
    -0.63
    mentaires
    -0.63
    dymyr
    -0.62
     समीक्षाएं
    -0.61
    든
    -0.60
    POSITIVE LOGITS
     للمعارف
    0.84
    ſelves
    0.80
    Nuorodos
    0.77
    numerusform
    0.76
     Anſ
    0.74
    ">'.$
    0.73
     BRARY
    0.72
     itſelf
    0.72
     himſelf
    0.71
     Kaufmann
    0.71
    Act Density 0.587%

    No Known Activations