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

    Neuronpedia

    INDEX
    Explanations

    numbers and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ectoria
    0.70
    떴
    0.68
     asymmetry
    0.65
     Basis
    0.65
     courbes
    0.64
     années
    0.63
     Pyr
    0.62
     basis
    0.62
     아니다
    0.62
    설
    0.62
    POSITIVE LOGITS
     exactly
    0.74
     हिंद
    0.62
    Wald
    0.62
    exactly
    0.61
     exatamente
    0.58
     Wald
    0.58
    WAB
    0.57
    wash
    0.57
     интер
    0.56
    玛
    0.56
    Act Density 0.184%

    No Known Activations