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

    Neuronpedia

    INDEX
    Explanations

    will of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     смеси
    1.29
     Tijdens
    1.29
    trashItem
    1.27
    та
    1.22
     rivets
    1.21
     viser
    1.20
    ب
    1.18
     Executives
    1.17
     dampak
    1.17
     tiens
    1.17
    POSITIVE LOGITS
    1
    1.84
    3
    1.66
    ಯ
    1.66
    ют
    1.59
    4
    1.57
    6
    1.56
    8
    1.54
    7
    1.54
    데
    1.52
    s
    1.52
    Act Density 0.001%

    No Known Activations