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

    Neuronpedia

    INDEX
    Explanations

    assessment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    页
    -0.07
     idade
    -0.07
     Ό
    -0.07
    aight
    -0.07
     prow
    -0.06
    eliminar
    -0.06
    رفت
    -0.06
     ES
    -0.06
    酒
    -0.06
     dinero
    -0.06
    POSITIVE LOGITS
    _translate
    0.07
     reco
    0.07
    мом
    0.07
     levy
    0.07
     assessed
    0.07
     assessment
    0.06
     Lesser
    0.06
     بسی
    0.06
    Station
    0.06
     atheist
    0.06
    Act Density 0.002%

    No Known Activations