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

    Neuronpedia

    INDEX
    Explanations

    code/configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Verbose
    -0.07
    ít
    -0.06
    UCKET
    -0.06
    .exe
    -0.06
     thicker
    -0.06
    =%.
    -0.06
    (tc
    -0.06
     Scotch
    -0.06
     resolve
    -0.06
    /modules
    -0.06
    POSITIVE LOGITS
    _factory
    0.07
     overshadow
    0.06
    аем
    0.06
     kabil
    0.06
    .SO
    0.06
    ，或
    0.06
     economist
    0.06
    няют
    0.06
     göl
    0.06
    ще
    0.06
    Act Density 0.035%

    No Known Activations