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

    Neuronpedia

    INDEX
    Explanations

    Code, punctuation, and quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     米
    -0.07
    ヶ
    -0.06
     Kosten
    -0.06
     paranoid
    -0.06
     largely
    -0.06
     bạc
    -0.06
     Česko
    -0.06
    _lit
    -0.06
    として
    -0.06
    geb
    -0.06
    POSITIVE LOGITS
    "People
    0.07
    _NETWORK
    0.06
    ”:
    0.06
     PAY
    0.06
     Promo
    0.06
     TO
    0.06
     Lad
    0.06
    _Ex
    0.06
     use
    0.06
    .cornerRadius
    0.06
    Act Density 0.000%

    No Known Activations