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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    复古
    -0.08
    功夫
    -0.07
    áticas
    -0.07
    AREN
    -0.07
    .linspace
    -0.07
    这段时间
    -0.07
    水稻
    -0.07
     conj
    -0.06
     seaborn
    -0.06
    轻轻地
    -0.06
    POSITIVE LOGITS
    Kir
    0.07
    recover
    0.07
    Creator
    0.06
    مست
    0.06
     Provider
    0.06
    kelig
    0.06
    (do
    0.06
    -$
    0.06
    Availability
    0.06
     FormBuilder
    0.06
    Act Density 0.014%

    No Known Activations