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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SQUARE
    -0.07
    НЯ
    -0.06
    зна
    -0.06
    وار
    -0.06
     accommodate
    -0.06
     plaque
    -0.06
     yan
    -0.06
     Jam
    -0.06
    fwrite
    -0.06
    (bl
    -0.06
    POSITIVE LOGITS
    ]])↵↵
    0.07
    เตอร
    0.07
    ()))
    0.06
    ıma
    0.06
    }/${
    0.06
    ฐ
    0.06
    ;}
    0.06
     GObject
    0.06
    *))
    0.06
     cucumber
    0.06
    Act Density 0.015%

    No Known Activations