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

    Neuronpedia

    INDEX
    Explanations

    can't quite recall/explain/name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thấy
    0.88
    看到
    0.88
    见过
    0.88
     دیده
    0.79
     gesehen
    0.79
    见到
    0.78
     views
    0.78
     see
    0.78
     betrachtet
    0.77
    views
    0.75
    POSITIVE LOGITS
    exact
    0.87
     уточ
    0.86
    正確
    0.85
     tepat
    0.81
    ame
    0.80
    verläss
    0.80
     exact
    0.80
    ikesh
    0.79
     exacta
    0.78
     सटीक
    0.76
    Act Density 0.019%

    No Known Activations