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

    Neuronpedia

    INDEX
    Explanations

    O

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HttpClient
    -0.07
    db
    -0.06
     Feet
    -0.06
    _ends
    -0.06
    uts
    -0.06
    MA
    -0.06
     sf
    -0.06
    icipants
    -0.06
    tables
    -0.06
    Rail
    -0.06
    POSITIVE LOGITS
     слово
    0.07
     Фед
    0.06
    ':"
    0.06
    !(
    0.06
    mekte
    0.06
     unequiv
    0.06
    _rewards
    0.06
    .PO
    0.06
    /how
    0.05
     adrenal
    0.05
    Act Density 0.003%

    No Known Activations