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

    Neuronpedia

    INDEX
    Explanations

    awards and honors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בא
    -0.07
     för
    -0.07
    掣
    -0.07
    �
    -0.07
    灯具
    -0.07
    ombok
    -0.07
     ш
    -0.06
    (Dialog
    -0.06
     путешеств
    -0.06
     Generally
    -0.06
    POSITIVE LOGITS
     sentir
    0.07
     =↵
    0.07
     capítulo
    0.07
     части
    0.07
     (?
    0.07
    cae
    0.07
    .createFrom
    0.07
     grip
    0.07
     Feel
    0.07
    味道
    0.06
    Act Density 0.037%

    No Known Activations