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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taxpayer
    -0.08
    に関
    -0.07
    PLEASE
    -0.07
    تنسي
    -0.07
     Dome
    -0.07
    𫰛
    -0.07
    shi
    -0.06
    /slider
    -0.06
    alian
    -0.06
    柠
    -0.06
    POSITIVE LOGITS
    reation
    0.07
    Prop
    0.07
     Ironically
    0.07
     breakfast
    0.06
    trecht
    0.06
    激发
    0.06
     awakened
    0.06
     parentId
    0.06
     가능한
    0.06
     problème
    0.06
    Act Density 0.001%

    No Known Activations