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

    Neuronpedia

    INDEX
    Explanations

    RETURN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eingang
    -0.08
     Sistema
    -0.08
     accounting
    -0.08
     Accounting
    -0.08
    Accounting
    -0.08
     mestre
    -0.08
     Det
    -0.07
     funnel
    -0.07
     yapmak
    -0.07
    国务院
    -0.07
    POSITIVE LOGITS
     únicamente
    0.09
    ただ
    0.09
     فقط
    0.08
     మాత్రమే
    0.08
     uniquement
    0.08
     лиш
    0.08
     Apenas
    0.08
     csak
    0.08
    だけ
    0.08
     gusa
    0.08
    Act Density 0.001%

    No Known Activations