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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their usage in various contexts

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

    messages.res

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.66
     faſt
    -0.55
     ſur
    -0.43
     ſta
    -0.42
    NSIndexPath
    -0.40
     conflits
    -0.40
     juſ
    -0.39
     وتسجيلات
    -0.39
    염
    -0.38
     pleaſure
    -0.38
    POSITIVE LOGITS
    principalColumn
    0.51
    fromnode
    0.48
     فريبيس
    0.47
     gantung
    0.47
    دانشنامهٔ
    0.44
    xrLabel
    0.43
    _'.$
    0.43
    elemField
    0.43
    ?}",
    0.43
    原始内容存档于
    0.43
    Act Density 0.084%

    No Known Activations