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

    Neuronpedia

    INDEX
    Explanations

    android

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feedback
    -0.07
    喘
    -0.07
     thở
    -0.07
    ehler
    -0.07
    :I
    -0.07
     antioxidant
    -0.07
    .E
    -0.07
    /dist
    -0.07
     Humanities
    -0.06
    שומר
    -0.06
    POSITIVE LOGITS
    或多
    0.07
     �
    0.07
     וכ
    0.07
    ReadStream
    0.07
    쬘
    0.06
    HasBeenSet
    0.06
    Пер
    0.06
    家庭
    0.06
     п
    0.06
    弥
    0.06
    Act Density 0.006%

    No Known Activations