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

    Neuronpedia

    INDEX
    Explanations

    People and relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    master
    -0.06
     кад
    -0.06
    沿
    -0.06
    weets
    -0.06
    .height
    -0.06
    pcs
    -0.06
     význam
    -0.06
    .include
    -0.06
     shouldBe
    -0.06
    جا
    -0.06
    POSITIVE LOGITS
    ουν
    0.07
    acimiento
    0.07
    _verbose
    0.07
    raison
    0.06
    ंध
    0.06
     NJ
    0.06
    ammen
    0.06
    sp
    0.06
    кам
    0.06
    liž
    0.06
    Act Density 0.104%

    No Known Activations