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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and programming structures

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

    median calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     交
    -0.41
     exchange
    -0.33
     Interchange
    -0.32
     interchange
    -0.32
     Tadeusz
    -0.32
    交換
    -0.32
    made
    -0.32
     exchanged
    -0.31
     šķ
    -0.31
     Exchange
    -0.31
    POSITIVE LOGITS
     فريبيس
    0.67
    principalColumn
    0.56
    adaptiveStyles
    0.55
    الدراسه
    0.54
     <=",
    0.53
     MainAxisSize
    0.50
     Италијани
    0.48
    IVEREF
    0.48
    ChildScrollView
    0.47
    imetry
    0.47
    Act Density 0.083%

    No Known Activations