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

    Neuronpedia

    INDEX
    Explanations

    availability of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tĩnh
    0.89
    么
    0.82
     इससे
    0.80
    ществует
    0.80
     соблю
    0.79
    都不是
    0.79
    囵
    0.79
    だけ
    0.78
     dennoch
    0.78
     bilhões
    0.78
    POSITIVE LOGITS
    на
    1.17
    ar
    1.05
    م
    1.02
    м
    0.98
    ان
    0.95
    ang
    0.92
    ou
    0.90
    t
    0.86
    з
    0.86
    el
    0.86
    Act Density 0.000%

    No Known Activations