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

    Neuronpedia

    INDEX
    Explanations

    acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JE
    -0.07
     прямо
    -0.07
    xEF
    -0.06
    .Man
    -0.06
    _GUID
    -0.06
    iste
    -0.06
     fwrite
    -0.06
     BU
    -0.06
    สก
    -0.06
    izados
    -0.06
    POSITIVE LOGITS
    -eslint
    0.06
    fact
    0.06
     useCallback
    0.06
    expo
    0.06
     Rivera
    0.06
    „M
    0.06
     desperately
    0.06
     res
    0.06
    _ALL
    0.06
    :UIControlEvent
    0.06
    Act Density 0.011%

    No Known Activations