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

    Neuronpedia

    INDEX
    Explanations

    Javascript methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    开心
    -0.08
    席执行
    -0.07
     sharing
    -0.07
     firstname
    -0.07
     incom
    -0.07
    窸
    -0.06
    ynchronous
    -0.06
    _HE
    -0.06
    أنش
    -0.06
    🎉
    -0.06
    POSITIVE LOGITS
    .iter
    0.07
     contours
    0.07
     Hard
    0.07
     жив
    0.07
     trava
    0.07
     depend
    0.07
     rua
    0.07
    �
    0.07
     Subway
    0.07
    *pow
    0.07
    Act Density 0.001%

    No Known Activations