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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oldsymbol
    0.59
    |\
    0.57
     మరి
    0.56
     കൂടുത
    0.55
    रातील
    0.55
     frequencies
    0.55
     horizons
    0.55
    频率
    0.55
     مربع
    0.55
    界的
    0.55
    POSITIVE LOGITS
    싫
    0.57
     Before
    0.55
     sebelum
    0.55
    0.55
    before
    0.54
     before
    0.54
    Before
    0.54
    前に
    0.54
    終了
    0.54
     Anschließend
    0.54
    Act Density 0.000%

    No Known Activations