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

    Neuronpedia

    INDEX
    Explanations

    defining concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     daca
    0.37
     resiliency
    0.36
     الب
    0.35
     aggior
    0.35
     হতাশ
    0.35
     panneau
    0.34
     déplacer
    0.34
     പിന്തുണ
    0.34
     অনেক
    0.34
    ア
    0.34
    POSITIVE LOGITS
     usually
    0.44
     обычно
    0.41
    usually
    0.39
     Usually
    0.37
     или
    0.36
     oneself
    0.36
     вследствие
    0.36
     meestal
    0.36
    ;"
    0.34
     suatu
    0.34
    Act Density 0.103%

    No Known Activations