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

    Neuronpedia

    INDEX
    Explanations

    Removable parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spicy
    -0.07
    积极推动
    -0.07
     Webster
    -0.07
    ,value
    -0.07
    벽
    -0.07
    placeholders
    -0.07
    学前教育
    -0.07
     dicks
    -0.06
    Ḳ
    -0.06
    -strokes
    -0.06
    POSITIVE LOGITS
    请
    0.07
    /user
    0.07
    炣
    0.07
    -transparent
    0.07
    につ
    0.07
     supposed
    0.07
    _detail
    0.07
    _Set
    0.07
    0.07
    _Class
    0.07
    Act Density 0.054%

    No Known Activations