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

    Neuronpedia

    INDEX
    Explanations

    links to publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tuberculous
    0.66
     presentato
    0.64
    舉辦
    0.63
    Zb
    0.63
    zij
    0.62
    Za
    0.59
     YE
    0.58
     FEBRUARY
    0.58
     стрельца
    0.57
     संगठ
    0.57
    POSITIVE LOGITS
    ቦች
    0.61
     ва
    0.60
     cogn
    0.59
     পেরে
    0.57
     Partial
    0.56
     isTestSource
    0.56
     partial
    0.56
    тук
    0.55
    /}{
    0.54
    eman
    0.54
    Act Density 0.020%

    No Known Activations