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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (root
    -0.07
     Zum
    -0.07
     POR
    -0.06
     Naval
    -0.06
    _DAT
    -0.06
     Guerrero
    -0.06
    ी.
    -0.06
    福利
    -0.06
     gentleman
    -0.06
    init
    -0.06
    POSITIVE LOGITS
     чего
    0.07
     viêm
    0.07
    성
    0.07
    .InnerException
    0.07
    alığı
    0.06
    ,:,
    0.06
    测
    0.06
    ๋
    0.06
    (Number
    0.06
     نقد
    0.06
    Act Density 0.001%

    No Known Activations