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

    Neuronpedia

    INDEX
    Explanations

    radiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parad
    -0.07
    "If
    -0.07
    (work
    -0.07
    )|(
    -0.06
    .PRO
    -0.06
     Billboard
    -0.06
    “If
    -0.06
     опред
    -0.06
    .pro
    -0.06
    .definition
    -0.06
    POSITIVE LOGITS
    glas
    0.06
     khá
    0.06
    Art
    0.06
     hair
    0.06
    感情
    0.06
    thon
    0.06
    .lt
    0.06
     beloved
    0.06
     molding
    0.06
     Mah
    0.06
    Act Density 0.004%

    No Known Activations