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

    Neuronpedia

    INDEX
    Explanations

    why is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XYZ
    0.43
    Dr
    0.42
     succeed
    0.42
    Each
    0.41
    ंजक
    0.41
    URAL
    0.41
    DON
    0.40
    Luther
    0.40
    NOT
    0.39
    Rooms
    0.39
    POSITIVE LOGITS
     फक्त
    0.45
     तभी
    0.44
    没有任何
    0.44
     일부
    0.41
     некоторым
    0.41
     ഒന്നും
    0.40
     kaik
    0.40
     something
    0.40
     sehingga
    0.40
     רבים
    0.39
    Act Density 0.011%

    No Known Activations