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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lever
    -0.07
    real
    -0.07
     equipe
    -0.06
    .enterprise
    -0.06
     Bes
    -0.06
    fe
    -0.06
     Mang
    -0.06
    ême
    -0.06
     beaucoup
    -0.06
     Dec
    -0.06
    POSITIVE LOGITS
     antibodies
    0.08
     reminders
    0.08
    譽
    0.07
    股东
    0.07
     antig
    0.07
    _corners
    0.07
     wrist
    0.07
    多多
    0.07
    襕
    0.07
    ὦ
    0.07
    Act Density 0.200%

    No Known Activations