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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sinus
    -0.07
     Humans
    -0.07
     rendered
    -0.07
     ensured
    -0.07
    .Logging
    -0.06
     Inn
    -0.06
     humans
    -0.06
     alteration
    -0.06
    culo
    -0.06
    .).
    -0.06
    POSITIVE LOGITS
     GM
    0.06
     nowadays
    0.06
    ¢
    0.06
     IBM
    0.06
    Toyota
    0.05
    ία
    0.05
    ('$
    0.05
    经验
    0.05
    IO
    0.05
     Occup
    0.05
    Act Density 0.000%

    No Known Activations