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

    Neuronpedia

    INDEX
    Explanations

    multilingual citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IPT
    0.40
     chí
    0.37
    Blood
    0.37
    IP
    0.36
    All
    0.35
    Radio
    0.35
    Network
    0.34
     Plow
    0.34
    Memor
    0.34
    朽
    0.34
    POSITIVE LOGITS
     специ
    0.44
     multiplicação
    0.43
     вчера
    0.41
     bulun
    0.39
     venc
    0.39
     подвод
    0.38
     অ
    0.38
    밂
    0.38
    ﺀ
    0.38
    今天
    0.37
    Act Density 0.000%

    No Known Activations