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

    Neuronpedia

    INDEX
    Explanations

    plural possessive, changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     בעי
    0.46
    remaining
    0.46
     orientated
    0.45
    isDisabled
    0.44
     جاری
    0.44
    verbrauch
    0.44
     هل
    0.43
     outflows
    0.43
     decarbon
    0.41
    beek
    0.41
    POSITIVE LOGITS
    ജ
    0.49
    Х
    0.47
    포
    0.47
    ദ
    0.47
    ミ
    0.47
    ඳ
    0.47
    Ա
    0.46
    ở
    0.46
     Pointe
    0.45
    ්
    0.45
    Act Density 0.001%

    No Known Activations