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

    Neuronpedia

    INDEX
    Explanations

    mal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     알고
    -0.07
     Republicans
    -0.07
     jelly
    -0.06
     bride
    -0.06
    Republicans
    -0.06
    _nbr
    -0.06
     Syrians
    -0.06
    ,address
    -0.06
     knife
    -0.06
    _prev
    -0.06
    POSITIVE LOGITS
     пунк
    0.07
     dropped
    0.06
    nEnter
    0.06
     Eddie
    0.06
    aucoup
    0.06
    />↵↵
    0.06
     ErrorResponse
    0.06
     основе
    0.06
     EFFECT
    0.06
    atural
    0.06
    Act Density 0.001%

    No Known Activations