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

    Neuronpedia

    INDEX
    Explanations

    html href and type

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dogs
    0.54
     layers
    0.53
    敎
    0.52
     ವ
    0.51
    rije
    0.51
    ají
    0.51
     শতাব্দ
    0.50
     Patten
    0.49
     pequ
    0.49
     붙
    0.49
    POSITIVE LOGITS
    ียม
    0.64
    スキー
    0.64
    वीर
    0.58
    ளைஞ
    0.57
     semelhante
    0.55
     cp
    0.54
     ternary
    0.54
     бесплатно
    0.54
    挈
    0.54
     arsine
    0.53
    Act Density 0.002%

    No Known Activations