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

    Neuronpedia

    INDEX
    Explanations

    various types of formatted comments or metadata in code

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

    Code comments with asterisks or hyphens

    np_acts-logits-general · gemini-2.0-flash

    comments and code headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     архивлан
    -0.94
     BoxFit
    -0.88
    دانشنامهٔ
    -0.86
    richTextPanel
    -0.84
    ьаж
    -0.83
     protoimpl
    -0.82
     ModelExpression
    -0.80
    Vidite
    -0.78
    kháu
    -0.76
     transfieras
    -0.74
    POSITIVE LOGITS
    ↵
    0.61
     J
    0.52
    ph
    0.51
     DR
    0.49
    лю
    0.49
    ----------------
    0.48
    წ
    0.47
    ذ
    0.45
     commun
    0.45
    ExecutionContext
    0.45
    Act Density 0.174%

    No Known Activations