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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values or indications of loss

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

    units and conversions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.55
     EconPapers
    -0.49
     ModelExpression
    -0.48
    testify
    -0.47
     CURIAM
    -0.47
     religieuses
    -0.43
    存于互联网档案馆
    -0.43
    styleType
    -0.42
    WireFormatLite
    -0.41
     himo
    -0.40
    POSITIVE LOGITS
    AutoresizingMask
    0.56
    ViewFeatures
    0.45
     Hins
    0.42
     tartalomajánló
    0.40
     '{@
    0.39
    RectangleBorder
    0.38
     Balls
    0.37
    飽
    0.36
     grima
    0.36
    ✉
    0.36
    Act Density 0.005%

    No Known Activations