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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usters
    -0.08
    Interstitial
    -0.07
    textarea
    -0.06
    chrono
    -0.06
    Om
    -0.06
    ARIANT
    -0.06
    (utils
    -0.06
    ForRow
    -0.06
     rst
    -0.06
    zers
    -0.06
    POSITIVE LOGITS
     CONSEQUENTIAL
    0.07
    (api
    0.06
    .matcher
    0.06
    jvu
    0.06
     bullet
    0.06
    .tc
    0.06
    ivar
    0.06
    ownik
    0.06
     samostat
    0.06
    -trans
    0.06
    Act Density 0.223%

    No Known Activations