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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Qui
    -0.06
     उ
    -0.06
    Spi
    -0.06
     dint
    -0.06
    グラ
    -0.06
    .Output
    -0.06
    osg
    -0.06
     ПО
    -0.05
     collaborate
    -0.05
    rece
    -0.05
    POSITIVE LOGITS
    ท
    0.08
     nghề
    0.08
     fileprivate
    0.07
     başlam
    0.07
     quyền
    0.07
     pornost
    0.07
     heures
    0.07
    صة
    0.07
    ฐ
    0.06
     manual
    0.06
    Act Density 0.036%

    No Known Activations