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

    Neuronpedia

    INDEX
    Explanations

    energy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trustees
    -0.07
    _schema
    -0.06
     núi
    -0.06
     seemingly
    -0.06
     seine
    -0.06
     будто
    -0.06
     premise
    -0.06
    ｗｗ
    -0.06
     revoked
    -0.06
     contradictions
    -0.06
    POSITIVE LOGITS
    $results
    0.07
    Aj
    0.07
     ky
    0.06
     MUSIC
    0.06
    translated
    0.06
    募
    0.06
     Music
    0.06
     Dancing
    0.06
    行動
    0.06
     Bj
    0.06
    Act Density 0.003%

    No Known Activations