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

    Neuronpedia

    INDEX
    Explanations

    fomenta la competencia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    い
    1.00
    ad
    0.98
    at
    0.95
    ot
    0.95
    um
    0.93
    ر
    0.91
    ਰ
    0.89
    ,
    0.89
    다
    0.83
    ר
    0.80
    POSITIVE LOGITS
    k
    1.00
    ن
    0.93
     enclose
    0.91
    n
    0.91
     défin
    0.85
     aumenta
    0.83
    }...
    0.82
    kého
    0.79
     rédu
    0.79
     devez
    0.77
    Act Density 0.000%

    No Known Activations