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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provider
    -0.07
    localctx
    -0.07
    ستان
    -0.07
    alth
    -0.07
     dress
    -0.07
    (@"
    -0.07
    usty
    -0.06
    -pattern
    -0.06
     preparedStatement
    -0.06
    ance
    -0.06
    POSITIVE LOGITS
     の
    0.07
    woff
    0.07
    placements
    0.07
    бро
    0.06
    北极
    0.06
    今年以来
    0.06
    ㄘ
    0.06
     uncertain
    0.06
     Giovanni
    0.06
     boosted
    0.06
    Act Density 0.230%

    No Known Activations