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
    statt
    -0.07
    -find
    -0.06
     myst
    -0.06
     RVA
    -0.06
    _Table
    -0.06
     Lis
    -0.06
    xp
    -0.06
    learn
    -0.05
    हन
    -0.05
     rehearsal
    -0.05
    POSITIVE LOGITS
    $o
    0.07
     %%↵
    0.06
    重要
    0.06
    PRESSION
    0.06
    プリ
    0.06
    高い
    0.06
     policemen
    0.06
     packets
    0.06
     Rough
    0.06
    idth
    0.06
    Act Density 0.003%

    No Known Activations