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

    Neuronpedia

    INDEX
    Explanations

    punctuation and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }`
    -0.07
    igenous
    -0.07
     Olive
    -0.06
     doomed
    -0.06
    оже
    -0.06
     Indigenous
    -0.06
     OV
    -0.06
     promotes
    -0.06
    ılmış
    -0.06
     experienced
    -0.06
    POSITIVE LOGITS
     Fiesta
    0.08
    0.07
    (signature
    0.07
    0.07
    JSONException
    0.06
     �
    0.06
    _succ
    0.06
    ifica
    0.06
    翻
    0.06
    menus
    0.06
    Act Density 0.000%

    No Known Activations