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

    Neuronpedia

    INDEX
    Explanations

    student requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     言
    0.46
    ͋
    0.42
    incer
    0.41
     parlare
    0.41
    統領
    0.41
    ǂ
    0.40
     पदार्थों
    0.40
     говорит
    0.39
    〈
    0.37
     ಚುನ
    0.37
    POSITIVE LOGITS
     rum
    0.39
    Awesome
    0.38
    وران
    0.37
     payback
    0.36
    crow
    0.36
    خوان
    0.36
     visitation
    0.35
    mts
    0.35
     excessive
    0.35
    Lum
    0.35
    Act Density 0.000%

    No Known Activations