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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Misc
    -0.06
    Practice
    -0.06
     wholes
    -0.06
     roles
    -0.06
     civil
    -0.06
     counterfeit
    -0.06
    uil
    -0.06
     Breaking
    -0.06
     "-",
    -0.06
    xor
    -0.05
    POSITIVE LOGITS
     прох
    0.07
     serm
    0.07
    apple
    0.07
    .NAME
    0.07
    注
    0.07
    _TRAIN
    0.07
     βιβ
    0.06
     případně
    0.06
     Bağ
    0.06
    飯店
    0.06
    Act Density 0.013%

    No Known Activations