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

    Neuronpedia

    INDEX
    Explanations

    `else {`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Noble
    0.62
     nécessairement
    0.58
     Callable
    0.58
     Canary
    0.58
    тельные
    0.58
     Veterinary
    0.57
     existentes
    0.56
    anque
    0.56
     Equestrian
    0.55
     Ancient
    0.55
    POSITIVE LOGITS
    μά
    0.47
     لح
    0.45
    improv
    0.45
     মাত্র
    0.45
    artwork
    0.44
    <0x99>
    0.44
    ecd
    0.44
     ينت
    0.44
    lif
    0.44
     خلال
    0.44
    Act Density 0.001%

    No Known Activations