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

    Neuronpedia

    INDEX
    Explanations

    cancellations and changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffe
    -0.08
     correspond
    -0.07
     Mes
    -0.07
    _binary
    -0.07
    лес
    -0.07
     cellspacing
    -0.07
     Correspond
    -0.07
     announce
    -0.07
     Alg
    -0.07
     shortcut
    -0.07
    POSITIVE LOGITS
    取消
    0.10
     Changes
    0.09
    Changes
    0.09
     გ
    0.09
    変更
    0.08
     adaptability
    0.08
     flexibility
    0.08
     changes
    0.08
     abortion
    0.08
    撤
    0.08
    Act Density 0.023%

    No Known Activations