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

    Neuronpedia

    INDEX
    Explanations

    describing humans or personal characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    几何
    0.35
    可视化
    0.33
    物理
    0.32
     системы
    0.32
    ToolStrip
    0.31
     инфраструк
    0.31
    散热
    0.30
     cinematographer
    0.30
    ୋ
    0.30
     উপকূল
    0.30
    POSITIVE LOGITS
     Biographical
    0.37
     인간
    0.37
     humain
    0.37
     humanas
    0.36
     personal
    0.36
     humana
    0.35
     mammalian
    0.35
     Personnel
    0.33
     Personal
    0.33
     نمی
    0.32
    Act Density 0.499%

    No Known Activations