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

    Neuronpedia

    INDEX
    Explanations

    add other text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ן
    0.78
    BE
    0.78
    蒎
    0.78
    TE
    0.75
    ICKET
    0.73
    amise
    0.73
    小时候
    0.73
    idet
    0.72
    क्यात
    0.72
    ieving
    0.72
    POSITIVE LOGITS
    ம்பரிய
    0.82
     limbo
    0.75
     Conn
    0.73
     VoIP
    0.73
     ultrap
    0.73
     `=`
    0.72
     gutters
    0.71
     detener
    0.71
     Schengen
    0.70
     निर्धारित
    0.69
    Act Density 0.001%

    No Known Activations