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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itis
    -0.08
    .credentials
    -0.08
    clerosis
    -0.08
    cler
    -0.08
    _credentials
    -0.07
     penit
    -0.07
    (credentials
    -0.07
    +'
    -0.07
     CWE
    -0.07
    ologen
    -0.07
    POSITIVE LOGITS
    վի
    0.10
    ,))↵
    0.08
     khác
    0.08
    吸
    0.08
    青青草
    0.08
     attracting
    0.08
     attracts
    0.08
     Интер
    0.08
    ригин
    0.08
     commerciale
    0.08
    Act Density 0.002%

    No Known Activations