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

    Neuronpedia

    INDEX
    Explanations

    Languages/Tribes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    هم
    -0.07
    'ils
    -0.07
    |↵↵
    -0.07
    624
    -0.06
    �
    -0.06
     Hat
    -0.06
    user
    -0.06
    ethod
    -0.06
    ни
    -0.06
    _ends
    -0.06
    POSITIVE LOGITS
    .tcp
    0.07
    basename
    0.07
    ![↵
    0.06
     Bands
    0.06
     Gand
    0.06
     incess
    0.06
    (wp
    0.06
    .quality
    0.06
    _POLICY
    0.06
    (Profile
    0.06
    Act Density 0.016%

    No Known Activations