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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     downt
    -0.06
     تاث
    -0.06
     silah
    -0.06
     такими
    -0.06
    ヘ
    -0.06
    ям
    -0.06
     деся
    -0.06
    ,nonatomic
    -0.06
    ecut
    -0.06
    �
    -0.05
    POSITIVE LOGITS
     Prom
    0.07
    )↵
    0.07
    لة
    0.07
    ZERO
    0.07
    MER
    0.07
    _For
    0.07
     tangible
    0.07
     For
    0.07
     perfor
    0.07
    Walking
    0.07
    Act Density 0.016%

    No Known Activations