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

    Neuronpedia

    INDEX
    Explanations

    plaque

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pressor
    -0.06
    osoph
    -0.06
    (summary
    -0.06
    ション
    -0.06
    ERSION
    -0.06
    ersen
    -0.06
    344
    -0.06
    (region
    -0.06
    Stream
    -0.05
    ассив
    -0.05
    POSITIVE LOGITS
    _REGEX
    0.07
     prav
    0.07
     Esta
    0.07
    .labelX
    0.07
    uč
    0.07
    ！",
    0.06
     Clark
    0.06
     rainy
    0.06
     vacant
    0.06
    RELATED
    0.06
    Act Density 0.002%

    No Known Activations