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

    Neuronpedia

    INDEX
    Explanations

    av

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     říj
    -0.06
     DateTime
    -0.06
    true
    -0.06
    .Category
    -0.06
    민주
    -0.06
     PROGRAM
    -0.06
     CORE
    -0.06
    _ME
    -0.06
     PRODUCTS
    -0.06
     thổ
    -0.06
    POSITIVE LOGITS
     Brenda
    0.07
     Stalin
    0.07
     tolerate
    0.06
    _option
    0.06
    _likelihood
    0.06
     Accom
    0.06
    Backup
    0.06
     concess
    0.06
     homosexual
    0.06
    亚
    0.06
    Act Density 0.000%

    No Known Activations