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

    Neuronpedia

    INDEX
    Explanations

    Kumar, Completion API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ות
    0.53
    지
    0.50
    وں
    0.49
    ul
    0.47
    서
    0.46
    त्र
    0.43
    기를
    0.43
    ું
    0.41
    ą
    0.41
    र
    0.41
    POSITIVE LOGITS
    0.51
     been
    0.48
    _
    0.38
     not
    0.38
    )
    0.37
    ؛
    0.35
    ،
    0.35
    Been
    0.34
    可以让
    0.34
     BEEN
    0.34
    Act Density 0.000%

    No Known Activations