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

    Neuronpedia

    INDEX
    Explanations

    political and economic control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Е
    0.51
    Α
    0.50
    Έ
    0.47
     odlič
    0.46
    레
    0.46
    혔
    0.46
    )||
    0.44
    ரா
    0.44
    ικού
    0.44
     পৃথিব
    0.44
    POSITIVE LOGITS
    slag
    0.53
    emotion
    0.53
    old
    0.52
    financial
    0.48
    swe
    0.47
    spring
    0.46
     فقط
    0.46
    awareness
    0.46
    affected
    0.45
    絫
    0.45
    Act Density 0.002%

    No Known Activations