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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gression
    -0.07
     Jo
    -0.06
     systematically
    -0.06
     Projects
    -0.06
    .assign
    -0.06
    -ed
    -0.06
    criteria
    -0.06
    Series
    -0.06
     Source
    -0.06
    Humans
    -0.06
    POSITIVE LOGITS
    こんにちは
    0.07
    онів
    0.07
    ulpt
    0.07
    rut
    0.06
    يكي
    0.06
    _WM
    0.06
     lyon
    0.06
     peas
    0.06
     persön
    0.06
    út
    0.06
    Act Density 0.003%

    No Known Activations