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

    Neuronpedia

    INDEX
    Explanations

    distribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Resources
    -0.08
    觃
    -0.07
     العمل
    -0.07
     phòng
    -0.07
    行動
    -0.07
     approach
    -0.07
     Kills
    -0.07
     getNext
    -0.07
     reactions
    -0.07
    _NR
    -0.06
    POSITIVE LOGITS
     conspic
    0.07
    апример
    0.07
     especially
    0.07
    став
    0.07
     consistently
    0.06
    ///////////////////////////////////////////////////////////////////////////////↵
    0.06
    chapter
    0.06
     unfortunately
    0.06
    Hierarchy
    0.06
    kte
    0.06
    Act Density 0.013%

    No Known Activations