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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kana
    -0.09
    さらに
    -0.09
    Kana
    -0.08
     Kle
    -0.08
    Kaz
    -0.08
    kids
    -0.08
     pili
    -0.07
    ikwa
    -0.07
    .gwt
    -0.07
     Pä
    -0.07
    POSITIVE LOGITS
     silky
    0.08
     collections
    0.08
     Add
    0.07
    אב
    0.07
     Saving
    0.07
    內
    0.07
     suav
    0.07
     Mouth
    0.07
     sombre
    0.07
    DISC
    0.07
    Act Density 0.001%

    No Known Activations