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

    Neuronpedia

    INDEX
    Explanations

    computer code/technical docs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tally
    -0.07
    handled
    -0.07
    нице
    -0.07
     endangered
    -0.06
    UILD
    -0.06
     rebuilt
    -0.06
    _ROUTE
    -0.06
    ymes
    -0.06
    hrs
    -0.06
     milion
    -0.06
    POSITIVE LOGITS
    칭
    0.07
    
    0.06
    _Start
    0.06
     Az
    0.06
    ok
    0.06
     removing
    0.06
    เคล
    0.06
    いい
    0.06
    さんが
    0.06
     Bars
    0.06
    Act Density 0.000%

    No Known Activations