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

    Neuronpedia

    INDEX
    Explanations

    new instructional cues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.82
    ιν
    0.72
    ال
    0.71
    های
    0.67
    サッカー
    0.66
    ுள்ளனர்
    0.66
    inney
    0.65
    كين
    0.63
    াং
    0.63
    ιών
    0.61
    POSITIVE LOGITS
     Epistle
    0.88
    }^{-
    0.81
     Marquess
    0.81
    southern
    0.81
     adiab
    0.80
    ㄓ
    0.80
    website
    0.79
    র্বর
    0.79
     aorta
    0.79
     hypothalamic
    0.79
    Act Density 0.002%

    No Known Activations