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

    Neuronpedia

    INDEX
    Explanations

    Spirit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _language
    -0.07
    _learn
    -0.06
    ีข
    -0.06
     Lottery
    -0.06
    BX
    -0.06
     internationally
    -0.06
     pun
    -0.06
    輪
    -0.06
     imperialism
    -0.06
    Gap
    -0.06
    POSITIVE LOGITS
    .ai
    0.07
    (Constructor
    0.06
    (IEnumerable
    0.06
    /nav
    0.06
    كيب
    0.06
    ē
    0.06
    授
    0.06
    جه
    0.06
     Shib
    0.06
     itibaren
    0.06
    Act Density 0.009%

    No Known Activations