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

    Neuronpedia

    INDEX
    Explanations

    DAMAGE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.08
     spectacle
    -0.07
     popcorn
    -0.07
    材
    -0.07
    azzi
    -0.06
    学费
    -0.06
    尬
    -0.06
    Because
    -0.06
     Nd
    -0.06
    _FRAGMENT
    -0.06
    POSITIVE LOGITS
    ashtra
    0.07
     pitchers
    0.07
    杕
    0.07
     clearer
    0.07
     없
    0.07
     увер
    0.07
     whe
    0.07
    适合自己
    0.07
    เหมาะ
    0.07
    也没有
    0.07
    Act Density 0.000%

    No Known Activations