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

    Neuronpedia

    INDEX
    Explanations

    server

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SHORT
    -0.07
    fault
    -0.07
     Auss
    -0.06
     defect
    -0.06
     ему
    -0.06
     ↵        ↵
    -0.06
     рей
    -0.06
     aka
    -0.06
    BigDecimal
    -0.06
     inters
    -0.06
    POSITIVE LOGITS
    _ERR
    0.08
    .prev
    0.07
     라
    0.07
     dek
    0.06
     finanzi
    0.06
    helpers
    0.06
    /sites
    0.06
    linik
    0.06
     पस
    0.06
    multi
    0.06
    Act Density 0.014%

    No Known Activations