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

    Neuronpedia

    INDEX
    Explanations

    specific programming terms and phrases related to functions and variables

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

    preceding verb conjugations

    np_acts-logits-general · gemini-2.0-flash

    verbs and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.79
    AccessorTable
    -0.78
    rrggbb
    -0.77
     <>",
    -0.75
    PreferredItem
    -0.74
    abetes
    -0.73
    +#+
    -0.72
    AddTagHelper
    -0.71
     WaitForSeconds
    -0.69
     forKey
    -0.69
    POSITIVE LOGITS
     be
    0.63
     is
    0.54
    kuje
    0.49
     are
    0.48
    volves
    0.48
     می
    0.43
     does
    0.41
     can
    0.40
    ould
    0.40
     tartalomajánló
    0.39
    Act Density 0.127%

    No Known Activations