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

    Neuronpedia

    INDEX
    Explanations

    Physical development and appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     these
    0.48
    시
    0.48
    _
    0.46
     Thị
    0.46
    my
    0.46
    모
    0.45
     came
    0.45
    ",
    0.44
    गंगा
    0.44
     cars
    0.43
    POSITIVE LOGITS
     хочется
    0.45
    ஷ்ய
    0.45
     хотим
    0.44
    ָד
    0.44
    DIY
    0.43
    られます
    0.42
    ガー
    0.42
    冑
    0.41
    ਟਰ
    0.40
    ਧ
    0.40
    Act Density 0.003%

    No Known Activations