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

    Neuronpedia

    INDEX
    Explanations

    specific topics or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     која
    0.67
    ↵↵
    0.63
     ενός
    0.56
     deceler
    0.55
     drizz
    0.54
     sezonie
    0.53
     descrito
    0.52
     pēc
    0.52
     Един
    0.52
    ᅡ
    0.52
    POSITIVE LOGITS
    ون
    0.75
    it
    0.66
    ט
    0.66
    ik
    0.64
     and
    0.63
    ville
    0.61
     It
    0.57
    ements
    0.57
    ные
    0.57
    这个
    0.57
    Act Density 0.344%

    No Known Activations