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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kot
    -0.07
     BET
    -0.07
    ация
    -0.06
     популяр
    -0.06
    /../
    -0.06
    قول
    -0.06
     Suz
    -0.06
    Ok
    -0.06
    neg
    -0.06
    (internal
    -0.06
    POSITIVE LOGITS
    ’nın
    0.07
    ancements
    0.07
     stojí
    0.06
     �
    0.06
     등을
    0.06
    YG
    0.06
     инт
    0.06
     istediğiniz
    0.06
    LOYEE
    0.06
    ILTER
    0.06
    Act Density 0.007%

    No Known Activations