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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     �
    -0.06
    952
    -0.06
     manoe
    -0.06
     Dro
    -0.06
     Transmit
    -0.06
     utilizes
    -0.06
     вигля
    -0.06
    گوی
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
     SECRET
    0.07
     feu
    0.06
    (addr
    0.06
    conversion
    0.06
    (serializers
    0.06
     Erotische
    0.06
    leccion
    0.06
    iges
    0.06
    asında
    0.06
    äge
    0.06
    Act Density 0.000%

    No Known Activations