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

    Neuronpedia

    INDEX
    Explanations

    Let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dày
    -0.07
     upside
    -0.07
    ظˆط
    -0.06
    (|
    -0.06
    安全
    -0.06
     faux
    -0.06
     vým
    -0.06
     uncompressed
    -0.06
     braking
    -0.06
    ارهای
    -0.06
    POSITIVE LOGITS
    osopher
    0.07
    TCP
    0.06
     LET
    0.06
    tax
    0.06
     Aç
    0.06
     argue
    0.06
    POSE
    0.06
     governed
    0.06
     argued
    0.06
    Caller
    0.06
    Act Density 0.018%

    No Known Activations