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

    Neuronpedia

    INDEX
    Explanations

    Jewish concepts and Hebrew phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    1.73
    ING
    1.67
    sens
    1.66
    s
    1.65
    so
    1.64
    ément
    1.62
    abouts
    1.61
    AND
    1.60
    থাৎ
    1.55
    supp
    1.54
    POSITIVE LOGITS
    ()=>{
    1.77
     Nuestros
    1.67
     genomen
    1.59
    >|</
    1.58
     Pokud
    1.57
    ah
    1.55
     mercy
    1.54
     verwend
    1.53
    >−</
    1.52
    >≥</
    1.52
    Act Density 0.007%

    No Known Activations