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

    Neuronpedia

    INDEX
    Explanations

    American

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /current
    -0.07
    _page
    -0.07
    anio
    -0.07
     quienes
    -0.06
    structors
    -0.06
    interval
    -0.06
    ۽
    -0.06
    Lead
    -0.06
     instancia
    -0.06
    不合格
    -0.06
    POSITIVE LOGITS
    私服
    0.08
    밤
    0.08
    用
    0.07
    抵抗力
    0.07
    似
    0.07
    -handle
    0.07
    StartPosition
    0.07
    厚厚
    0.07
    -\
    0.07
     called
    0.07
    Act Density 0.012%

    No Known Activations