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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical values or parameters in a coding context

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

    NSNumber class and gamma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Incon
    -0.60
     GAC
    -0.56
    isEqualTo
    -0.54
    tagHelper
    -0.52
     Tripp
    -0.52
     TMC
    -0.51
    incon
    -0.50
     Avid
    -0.50
    INDU
    -0.50
     integ
    -0.50
    POSITIVE LOGITS
     ở
    1.86
     Ở
    1.58
    Ở
    1.30
    ở
    0.90
    อยู่
    0.71
    อยู่ใน
    0.63
    处
    0.60
     tässä
    0.60
     Verhältnisse
    0.59
     berada
    0.58
    Act Density 0.002%

    No Known Activations