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

    Neuronpedia

    INDEX
    Explanations

    restricted knowledge nuclear weapons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ేశ
    0.44
    𝐪
    0.44
     dragState
    0.43
    ሰው
    0.43
     рису
    0.43
    ოგ
    0.43
    бат
    0.42
     sobbing
    0.42
    樵
    0.42
    ក្រោម
    0.42
    POSITIVE LOGITS
    ＼
    0.42
    :
    0.41
    ;
    0.41
    olutions
    0.38
     প্রাণে
    0.38
    beans
    0.38
    ——
    0.37
    apor
    0.37
    weather
    0.37
    umers
    0.37
    Act Density 0.005%

    No Known Activations