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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    birthdate
    -0.07
    icensing
    -0.07
    _DRAW
    -0.06
     Vak
    -0.06
    Avoid
    -0.06
     зависимости
    -0.06
     relate
    -0.06
     Stan
    -0.06
     먼저
    -0.06
    Demand
    -0.06
    POSITIVE LOGITS
    řila
    0.07
    angles
    0.07
    コード
    0.07
    스티
    0.06
     sop
    0.06
     findById
    0.06
     scoop
    0.06
     ソ
    0.06
     spelled
    0.06
    AGED
    0.06
    Act Density 0.073%

    No Known Activations