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

    Neuronpedia

    INDEX
    Explanations

    html/css code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cens
    0.74
     싫
    0.72
     T
    0.68
    隸
    0.68
    }{\
    0.66
     Tek
    0.65
    }`
    0.65
    }^{\
    0.64
     spire
    0.63
     rational
    0.63
    POSITIVE LOGITS
    ્ય
    0.78
     टीस्पून
    0.78
     ভীষণ
    0.76
    XVI
    0.76
    🏆
    0.73
    nji
    0.73
     этим
    0.72
     باندې
    0.72
     capítulos
    0.71
     sábado
    0.71
    Act Density 0.021%

    No Known Activations