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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mapping
    -0.07
    机会
    -0.06
     Capital
    -0.06
     aprox
    -0.06
     ----------------
    -0.06
     Αρχ
    -0.06
     Mapping
    -0.06
    ________________
    -0.06
    (concat
    -0.06
    仔
    -0.06
    POSITIVE LOGITS
     Dul
    0.07
    owa
    0.06
     spender
    0.06
    $t
    0.06
     德
    0.06
     أبو
    0.06
     vase
    0.06
    jpeg
    0.06
    …↵↵↵
    0.06
    ainer
    0.06
    Act Density 0.004%

    No Known Activations