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

    Neuronpedia

    INDEX
    Explanations

    most basic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oppure
    0.22
     összes
    0.19
     অথবা
    0.19
     अथवा
    0.19
     dividers
    0.18
    ），
    0.18
     ovary
    0.18
     outset
    0.17
     =>
    0.17
    ’
    0.17
    POSITIVE LOGITS
    మంది
    0.19
    వరకు
    0.19
    ס
    0.19
     вполне
    0.17
    ሚ
    0.16
     pequeño
    0.16
    с
    0.16
    реа
    0.16
    л
    0.16
    简单的
    0.16
    Act Density 1.922%

    No Known Activations