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

    Neuronpedia

    INDEX
    Explanations

    candidate for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FindingsResponse
    0.58
    leda
    0.57
     مي
    0.55
     ياس
    0.54
     אפ
    0.54
    rollo
    0.51
     הק
    0.50
    كي
    0.50
     gelt
    0.49
    kwik
    0.48
    POSITIVE LOGITS
    IVERSITY
    0.60
     Ünivers
    0.55
    ত
    0.54
     Regions
    0.53
    ICK
    0.53
    瀆
    0.52
     Serializable
    0.51
     univers
    0.50
     Serialize
    0.50
    IES
    0.49
    Act Density 0.001%

    No Known Activations