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

    Neuronpedia

    INDEX
    Explanations

    siege weaponry catapults slingshots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ما
    0.86
    ang
    0.84
    ي
    0.79
    os
    0.79
    لا
    0.78
    ю
    0.77
    리
    0.74
    сто
    0.73
    ח
    0.73
    í
    0.73
    POSITIVE LOGITS
    '
    0.88
     catapult
    0.73
    iciencia
    0.64
     relieves
    0.63
     acrobat
    0.63
    ,
    0.61
     Version
    0.61
     propr
    0.61
    ፈር
    0.61
     final
    0.61
    Act Density 0.002%

    No Known Activations