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

    Neuronpedia

    INDEX
    Explanations

    agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تو
    1.07
    ে
    1.01
    ری
    0.97
    ط
    0.93
    ה
    0.93
     quarterfinals
    0.91
    i
    0.88
    ت
    0.88
    े
    0.87
    то
    0.87
    POSITIVE LOGITS
     _;
    0.90
    भूत
    0.88
     Cess
    0.88
     voces
    0.87
     ocurr
    0.87
     <!--
    0.86
     asimismo
    0.84
    ,_-
    0.83
     Certificates
    0.83
     capítulos
    0.83
    Act Density 0.002%

    No Known Activations