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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hel
    -0.07
     CJ
    -0.07
     Mod
    -0.07
     ℝ
    -0.06
    Estado
    -0.06
    žen
    -0.06
    serial
    -0.06
    лива
    -0.06
     VAL
    -0.06
    Som
    -0.06
    POSITIVE LOGITS
    /auth
    0.07
    tí
    0.06
     كه
    0.06
    (userName
    0.06
     depicting
    0.06
    tü
    0.06
     inline
    0.06
    ordion
    0.06
    -container
    0.06
    ('--
    0.06
    Act Density 0.034%

    No Known Activations