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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    folios
    -0.07
     числе
    -0.06
    روف
    -0.06
    Commands
    -0.06
     arenas
    -0.06
    ,row
    -0.06
     vůbec
    -0.06
    ăng
    -0.06
    staking
    -0.06
    leştir
    -0.06
    POSITIVE LOGITS
     Uni
    0.07
    Sil
    0.07
    .Encode
    0.06
    (Object
    0.06
    vím
    0.06
     tä
    0.06
    [:,:
    0.06
     розповід
    0.06
     drains
    0.06
     меж
    0.06
    Act Density 0.000%

    No Known Activations