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

    Neuronpedia

    INDEX
    Explanations

    Games

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TestCase
    -0.07
    [len
    -0.07
     incompet
    -0.07
     حر
    -0.07
     infiltr
    -0.07
     prejudice
    -0.07
     tube
    -0.07
     petals
    -0.07
     geen
    -0.07
    元件
    -0.07
    POSITIVE LOGITS
    ��
    0.07
    遵义
    0.06
     zeigt
    0.06
    _push
    0.06
    PDO
    0.06
    N
    0.06
    static
    0.06
    进出口
    0.06
    timeline
    0.06
     Daily
    0.06
    Act Density 0.003%

    No Known Activations