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

    Neuronpedia

    INDEX
    Explanations

    suggesting AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    乐
    0.45
    樂
    0.45
    다
    0.44
     missão
    0.43
    场景
    0.43
    לי
    0.43
     మీరు
    0.42
     кантора
    0.42
    icato
    0.42
    কে
    0.42
    POSITIVE LOGITS
     Bulgaria
    0.52
    gué
    0.47
     तस्वीरें
    0.46
    欲しい
    0.45
     And
    0.45
     pudd
    0.44
    વાલ
    0.43
     catégories
    0.41
     Sandberg
    0.41
     Bulgarian
    0.40
    Act Density 0.003%

    No Known Activations