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

    Neuronpedia

    INDEX
    Explanations

    punk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Faculty
    0.55
    ပါ
    0.54
    郧
    0.54
    کا
    0.53
    кину
    0.53
    を務
    0.53
     modo
    0.52
    קס
    0.52
    اري
    0.51
    пка
    0.51
    POSITIVE LOGITS
     punk
    0.73
    ors
    0.68
    sthe
    0.60
    cl
    0.59
    ially
    0.58
     Punk
    0.58
    bies
    0.56
     orch
    0.55
    il
    0.55
    punk
    0.55
    Act Density 0.002%

    No Known Activations