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

    Neuronpedia

    INDEX
    Explanations

    optional parameters in documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ZT
    0.73
    がつ
    0.71
    ({});
    0.70
     पकड़
    0.66
     observed
    0.65
    ZV
    0.63
    jackson
    0.62
     Observed
    0.62
     conserver
    0.61
    ごと
    0.61
    POSITIVE LOGITS
     vir
    0.87
     baie
    0.87
     hulle
    0.85
    skou
    0.81
     nie
    0.80
     jy
    0.77
     wê
    0.77
     ek
    0.76
     kategorie
    0.75
    oue
    0.75
    Act Density 0.059%

    No Known Activations