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

    Neuronpedia

    INDEX
    Explanations

    data tables and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ứng
    -0.07
    收
    -0.07
    RuleContext
    -0.06
     dims
    -0.06
    doctrine
    -0.06
    -fetch
    -0.06
    duced
    -0.06
    _verification
    -0.06
    ожет
    -0.06
    handlers
    -0.06
    POSITIVE LOGITS
     MLB
    0.07
    pecia
    0.06
    :this
    0.06
    UpdateTime
    0.06
     cleanly
    0.06
    patients
    0.06
    丝
    0.06
    ційного
    0.06
     Mädchen
    0.06
     mnemonic
    0.06
    Act Density 0.047%

    No Known Activations