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

    Neuronpedia

    INDEX
    Explanations

    green

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hol
    -0.07
     pale
    -0.07
    嘹
    -0.07
     Continuous
    -0.06
    Header
    -0.06
    阂
    -0.06
    urn
    -0.06
    �от
    -0.06
    udem
    -0.06
     Hen
    -0.06
    POSITIVE LOGITS
     cortex
    0.08
    詹姆斯
    0.07
     "`
    0.07
    _methods
    0.07
    (inner
    0.07
    -global
    0.07
     RAW
    0.07
    seconds
    0.07
     consoles
    0.07
    ство
    0.07
    Act Density 0.002%

    No Known Activations