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

    Neuronpedia

    INDEX
    Explanations

    -known

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coun
    -0.07
    ixture
    -0.07
     محل
    -0.07
    Args
    -0.07
     stati
    -0.07
    当局
    -0.07
     stał
    -0.07
     Ü
    -0.06
    不算
    -0.06
    炭
    -0.06
    POSITIVE LOGITS
    Knife
    0.07
    ڃ
    0.06
     apis
    0.06
    _workers
    0.06
    ("",
    0.06
     {},
    0.06
    ENS
    0.06
    known
    0.06
    KT
    0.06
    ㎘
    0.06
    Act Density 0.026%

    No Known Activations