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

    Neuronpedia

    INDEX
    Explanations

    formatting patterns used in functions and output statements in programming

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

    free and new and addr

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.81
    +#+
    -0.80
    tagHelperRunner
    -0.78
    ValueStyle
    -0.75
     المعيارى
    -0.74
    styleType
    -0.66
    Билгалдахарш
    -0.66
    RefNanny
    -0.63
    RegressionTest
    -0.61
     esternos
    -0.61
    POSITIVE LOGITS
     sons
    0.35
     Pit
    0.34
     tandem
    0.33
    PositiveButton
    0.32
     pit
    0.32
     claims
    0.31
     fig
    0.31
    ReadWrite
    0.31
     ce
    0.31
     ca
    0.30
    Act Density 0.017%

    No Known Activations