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

    Neuronpedia

    INDEX
    Explanations

    Incoherent text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eming
    -0.29
    家æĹı
    -0.27
    alling
    -0.25
    HEME
    -0.25
    anton
    -0.25
    æĺİ
    -0.24
     Spo
    -0.24
     quantitative
    -0.24
     family
    -0.24
     Alle
    -0.23
    POSITIVE LOGITS
    说æĪij
    0.28
    osh
    0.28
    odiac
    0.27
    æŶåĪ»
    0.25
     %+
    0.25
    uably
    0.25
    zial
    0.25
    å¹³åĿĩæ°´å¹³
    0.25
    .DoesNotExist
    0.24
    kdir
    0.24
    Act Density 0.124%

    No Known Activations