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

    Neuronpedia

    INDEX
    Explanations

    creating specific content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     или
    0.41
     یا
    0.40
     같다
    0.39
     unable
    0.39
     sheds
    0.39
     or
    0.38
     hoặc
    0.38
     혹은
    0.38
     takes
    0.37
     होईल
    0.37
    POSITIVE LOGITS
    MJX
    0.44
    MODKEY
    0.42
    pJ
    0.41
    γων
    0.41
    ollowing
    0.41
     सीई
    0.41
    ্ের
    0.41
    <unused66>
    0.41
    inians
    0.41
    쟈
    0.40
    Act Density 0.000%

    No Known Activations