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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     বৃদ্ধি
    -0.08
    ола
    -0.08
     deportes
    -0.08
    সহ
    -0.07
     clé
    -0.07
     কর্ত
    -0.07
    лекс
    -0.07
     incont
    -0.07
     RD
    -0.07
     возбуж
    -0.07
    POSITIVE LOGITS
     approximation
    0.09
    Approx
    0.09
     approxim
    0.08
    approx
    0.08
     funniest
    0.08
     शिव
    0.08
    Animated
    0.08
     таму
    0.08
    ativi
    0.08
    २०
    0.08
    Act Density 0.002%

    No Known Activations