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

    Neuronpedia

    INDEX
    Explanations

    Proof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ent
    -0.07
     propre
    -0.06
     enforcement
    -0.06
     пром
    -0.06
     náměstí
    -0.06
    От
    -0.06
    ニニ
    -0.06
     กำ
    -0.06
    iệng
    -0.06
     Sé
    -0.06
    POSITIVE LOGITS
    okrat
    0.07
    .AUTH
    0.07
    .bottom
    0.07
     Turks
    0.06
     heroin
    0.06
     aggravated
    0.06
     deleting
    0.06
    queue
    0.06
    선을
    0.06
    "x
    0.06
    Act Density 0.096%

    No Known Activations