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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    willReturn
    -0.06
    895
    -0.06
     emission
    -0.06
     عباس
    -0.06
    ulpt
    -0.06
     estimation
    -0.06
    (opts
    -0.06
     Welfare
    -0.06
    Between
    -0.06
    TRUE
    -0.06
    POSITIVE LOGITS
     indexed
    0.10
     indexing
    0.09
     Indexed
    0.08
     indexer
    0.07
    Indexed
    0.07
     dred
    0.07
     acquitted
    0.07
    ationToken
    0.07
     сор
    0.07
    _YUV
    0.06
    Act Density 0.005%

    No Known Activations