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

    Neuronpedia

    INDEX
    Explanations

    say "capitalized titles"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    奇
    -0.06
    ren
    -0.06
    iber
    -0.06
     factual
    -0.06
    DV
    -0.06
    ee
    -0.06
     helium
    -0.06
    ển
    -0.06
     P
    -0.06
     الظ
    -0.06
    POSITIVE LOGITS
    _startup
    0.07
    .ns
    0.07
    )){↵
    0.07
    WHITE
    0.07
    withstanding
    0.06
    /li
    0.06
     stops
    0.06
     scary
    0.06
    ('{{
    0.06
    .ColumnStyles
    0.06
    Act Density 0.044%

    No Known Activations