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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    user
    -0.08
     intensely
    -0.07
    (cps
    -0.07
    PathParam
    -0.07
    魔法师和
    -0.06
    rä
    -0.06
    @index
    -0.06
     quickly
    -0.06
     femme
    -0.06
    借款人
    -0.06
    POSITIVE LOGITS
    ation
    0.07
    宇宙
    0.07
     Glory
    0.07
    舆论
    0.07
    显示
    0.07
    odie
    0.07
    べき
    0.07
    مواجه
    0.07
    _cont
    0.07
    otify
    0.07
    Act Density 0.103%

    No Known Activations