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

    Neuronpedia

    INDEX
    Explanations

    witness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Portugal
    -0.07
     Oracle
    -0.06
     rub
    -0.06
    dub
    -0.06
     kao
    -0.06
    開発
    -0.06
    Transactional
    -0.06
     سبک
    -0.06
     účet
    -0.06
    .cid
    -0.06
    POSITIVE LOGITS
     witnesses
    0.10
     witness
    0.10
     Witness
    0.07
     Witnesses
    0.07
    491
    0.07
     Dexter
    0.07
    ßen
    0.06
    (route
    0.06
     toughest
    0.06
     excessive
    0.06
    Act Density 0.002%

    No Known Activations