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

    Neuronpedia

    INDEX
    Explanations

    copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ereço
    -0.08
    adresse
    -0.08
     Św
    -0.07
    💍
    -0.07
     ARRAY
    -0.07
     hookers
    -0.07
     Pavel
    -0.07
    最低
    -0.07
    метр
    -0.07
     resend
    -0.07
    POSITIVE LOGITS
    dbe
    0.07
    菰
    0.07
     Disease
    0.07
    黍
    0.07
    /
↵
    0.07
    淦
    0.07
    减值
    0.07
    -------↵
    0.07
     operations
    0.07
    воль
    0.07
    Act Density 0.000%

    No Known Activations