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

    Neuronpedia

    INDEX
    Explanations

    blocks of code or programming constructs

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

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſchen
    -0.64
    gridColumn
    -0.61
    clerView
    -0.61
     betweenstory
    -0.59
    ſelf
    -0.59
     UIColor
    -0.59
    OOTDTY
    -0.58
     KPK
    -0.58
     Majefty
    -0.58
    ロウィン
    -0.57
    POSITIVE LOGITS
    The
    0.63
    For
    0.52
    An
    0.50
    In
    0.49
    Then
    0.48
     The
    0.47
    HasAnnotation
    0.46
    if
    0.45
    Using
    0.45
    On
    0.45
    Act Density 0.031%

    No Known Activations