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

    Neuronpedia

    INDEX
    Explanations

    word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     traffic
    -0.08
     Європ
    -0.07
    .algorithm
    -0.07
     dokument
    -0.06
    反应
    -0.06
    issors
    -0.06
     hayata
    -0.06
     timed
    -0.06
    цами
    -0.06
     pollut
    -0.06
    POSITIVE LOGITS
    !:
    0.06
    отор
    0.06
     tern
    0.06
    ément
    0.06
    Done
    0.06
    prints
    0.06
     hopes
    0.06
    Song
    0.06
    krom
    0.06
     Isa
    0.06
    Act Density 0.000%

    No Known Activations