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

    Neuronpedia

    INDEX
    Explanations

    monthly or annual periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     մաս
    0.48
    ൺലൈ
    0.47
    𝓃
    0.47
    𝕤
    0.46
     fyz
    0.46
    䣷
    0.45
     لائ
    0.45
    會在
    0.44
     مربع
    0.44
     EACH
    0.43
    POSITIVE LOGITS
    /
    0.63
     or
    0.58
     или
    0.55
     किंवा
    0.55
     veya
    0.52
    或其他
    0.52
     capabilities
    0.51
     또는
    0.50
     અથવા
    0.50
     alebo
    0.49
    Act Density 0.000%

    No Known Activations