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

    Neuronpedia

    INDEX
    Explanations

    hate groups and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ayers
    0.70
    dfunding
    0.67
     возраст
    0.67
     ejempl
    0.65
    臤
    0.62
     age
    0.62
    வனாக
    0.61
    cJ
    0.61
    डेंगू
    0.60
    খি
    0.60
    POSITIVE LOGITS
    Poly
    0.79
     poly
    0.77
     Poly
    0.74
    poly
    0.72
    Eigen
    0.70
    Buffered
    0.67
    Polygon
    0.65
     Ashken
    0.65
     पॉली
    0.64
    Peg
    0.64
    Act Density 0.016%

    No Known Activations