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

    Neuronpedia

    INDEX
    Explanations

    genuine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hero
    -0.07
    Arduino
    -0.06
    Write
    -0.06
    oupon
    -0.06
     critic
    -0.06
    analy
    -0.06
    範
    -0.06
    Nom
    -0.06
    ker
    -0.06
     hiatus
    -0.06
    POSITIVE LOGITS
     unintention
    0.06
    ouflage
    0.06
    saldo
    0.06
    _ind
    0.06
    .patient
    0.06
     Instrument
    0.06
     بالق
    0.06
    .LinearLayoutManager
    0.06
    .getOrElse
    0.06
     contributing
    0.06
    Act Density 0.002%

    No Known Activations