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

    Neuronpedia

    INDEX
    Explanations

    gridlines or lines in plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verte
    0.38
    বুব
    0.38
     map
    0.38
    [(
    0.37
     Butch
    0.36
     dimiliki
    0.36
     dept
    0.35
    ಲ್ಲು
    0.35
     ब्यू
    0.35
     Verhalten
    0.35
    POSITIVE LOGITS
    ≐
    0.41
     كيف
    0.37
    imek
    0.37
    atem
    0.37
    мии
    0.37
     सीक्व
    0.37
     በጥ
    0.37
    omeness
    0.36
    垁
    0.36
     سق
    0.35
    Act Density 0.000%

    No Known Activations