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

    Neuronpedia

    INDEX
    Explanations

    words starting with All

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    داری
    0.39
    꼰
    0.39
    涹
    0.39
     erred
    0.38
    හෙ
    0.37
    رش
    0.37
     冖
    0.37
     }.
    0.36
     وسط
    0.36
    alık
    0.35
    POSITIVE LOGITS
     All
    0.61
    All
    0.53
    iances
    0.52
    igator
    0.52
    uvial
    0.49
    uding
    0.47
    ograft
    0.46
     Aller
    0.42
    getAll
    0.42
    គ្នា
    0.40
    Act Density 0.015%

    No Known Activations