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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﺦ
    -0.06
    紫外
    -0.06
    _DOT
    -0.06
    >');
    -0.06
    糠
    -0.06
    (collection
    -0.06
    (token
    -0.06
    ileo
    -0.06
    (models
    -0.06
    _than
    -0.06
    POSITIVE LOGITS
    еп
    0.07
    𝐻
    0.07
     Clock
    0.07
     HT
    0.07
     Every
    0.07
    .Fetch
    0.06
    astery
    0.06
     disgrace
    0.06
     şikayet
    0.06
    Is
    0.06
    Act Density 0.027%

    No Known Activations