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

    Neuronpedia

    INDEX
    Explanations

    science fiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    妖
    -0.08
    鋼
    -0.07
    ραβ
    -0.07
     Thompson
    -0.07
    لی
    -0.07
    ेष
    -0.07
     ◎
    -0.06
     ΔΗΜ
    -0.06
    _RF
    -0.06
    آم
    -0.06
    POSITIVE LOGITS
     elabor
    0.07
    .pyplot
    0.06
     ming
    0.06
    @↵↵
    0.06
    ていた
    0.06
     civilian
    0.06
     Sunni
    0.06
    travel
    0.06
     světa
    0.05
     활동
    0.05
    Act Density 0.110%

    No Known Activations