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

    Neuronpedia

    INDEX
    Explanations

    waitKey

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Myers
    -0.07
     aValue
    -0.07
     trendy
    -0.07
     Blair
    -0.06
     Hass
    -0.06
     jokes
    -0.06
     Click
    -0.06
     th�
    -0.06
     Joker
    -0.06
     využí
    -0.06
    POSITIVE LOGITS
    artifact
    0.07
    arme
    0.07
     deception
    0.06
    .Fecha
    0.06
    Political
    0.06
    _primitive
    0.06
    _charge
    0.06
    Initial
    0.06
    лада
    0.06
     traditions
    0.06
    Act Density 0.002%

    No Known Activations