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

    Neuronpedia

    INDEX
    Explanations

    auto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     바탕
    0.95
     oso
    0.87
    妳
    0.83
     oscillators
    0.83
     상
    0.82
     biomed
    0.82
    ्ल
    0.81
     Didier
    0.81
     सलूशन
    0.80
     flanges
    0.80
    POSITIVE LOGITS
    н
    1.01
    ли
    0.85
    Pur
    0.85
    Liability
    0.84
    の場合
    0.82
     וע
    0.82
    д
    0.82
    름
    0.80
    ق
    0.79
    Color
    0.77
    Act Density 0.001%

    No Known Activations