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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đạt
    -0.06
    уй
    -0.06
    .Driver
    -0.06
    _reward
    -0.06
    macen
    -0.06
     Ot
    -0.06
    Atual
    -0.06
     تبدیل
    -0.06
     quan
    -0.06
    ія
    -0.06
    POSITIVE LOGITS
     органов
    0.07
     Trigger
    0.07
     frightening
    0.07
    astically
    0.06
     honorable
    0.06
    华
    0.06
    –
    0.06
    ิจกรรม
    0.06
    .FlatAppearance
    0.06
     Hak
    0.06
    Act Density 0.004%

    No Known Activations