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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and functions

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

    mathematical expressions and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Robb
    -0.33
    ->___
    -0.32
    /*!
    -0.31
     ço
    -0.30
    torn
    -0.30
     bete
    -0.30
    IsMutable
    -0.30
    Present
    -0.29
    følge
    -0.29
     spro
    -0.29
    POSITIVE LOGITS
     H
    0.86
    setH
    0.83
    H
    0.82
     h
    0.81
     hh
    0.65
    maxHeight
    0.59
     HttpHeaders
    0.58
     maxHeight
    0.58
     getHeight
    0.58
    h
    0.58
    Act Density 0.163%

    No Known Activations