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

    Neuronpedia

    INDEX
    Explanations

    second item in a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     управління
    0.43
    ków
    0.42
    䒷
    0.42
     conglomerate
    0.41
    tsky
    0.41
     submarine
    0.39
     заседа
    0.39
    ষুধ
    0.38
    ње
    0.38
     essays
    0.38
    POSITIVE LOGITS
     altres
    0.42
    二是
    0.42
     Juga
    0.41
    ⒉
    0.41
     altri
    0.39
     Leute
    0.39
    unov
    0.39
     mel
    0.38
     Elemente
    0.38
     الثاني
    0.38
    Act Density 0.157%

    No Known Activations