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

    Neuronpedia

    INDEX
    Explanations

    advice and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seventh
    -0.07
     Nikol
    -0.07
     Bog
    -0.07
     NAFTA
    -0.06
    inski
    -0.06
    Destroy
    -0.06
    Arg
    -0.06
     Euro
    -0.06
     strchr
    -0.06
     Hiro
    -0.06
    POSITIVE LOGITS
    (Exception
    0.07
     terrain
    0.06
    contexts
    0.06
    ��
    0.06
    вий
    0.06
    jon
    0.06
    맞
    0.06
    (layers
    0.06
     juste
    0.06
     موفق
    0.06
    Act Density 0.002%

    No Known Activations