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

    Neuronpedia

    INDEX
    Explanations

    multi-language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.55
     nedenle
    1.49
    ない
    1.48
    fotos
    1.42
    ી
    1.42
    et
    1.41
    ação
    1.36
    aal
    1.31
    ে
    1.30
    ielles
    1.29
    POSITIVE LOGITS
    它
    1.41
    なる
    1.39
    ্ভব
    1.30
    िट
    1.30
    ل
    1.26
     respet
    1.23
    ลอง
    1.23
    )],
    1.20
    ראל
    1.20
    רי
    1.19
    Act Density 0.000%

    No Known Activations