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

    Neuronpedia

    INDEX
    Explanations

    code comments and memoization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    และ
    0.60
     и
    0.50
    和服务
    0.50
     आणि
    0.49
    and
    0.47
    ius
    0.47
    ag
    0.46
    world
    0.45
    gu
    0.44
     और
    0.44
    POSITIVE LOGITS
     judgements
    0.48
     judgement
    0.45
     sone
    0.44
     sucess
    0.43
     trono
    0.42
     imparting
    0.42
     yukarı
    0.41
     عند
    0.41
     saada
    0.40
     representing
    0.40
    Act Density 0.005%

    No Known Activations