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

    Neuronpedia

    INDEX
    Explanations

    focus on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ંદર
    0.46
     ಕೆಲವು
    0.44
    ளையும்
    0.44
    ından
    0.42
    可以在
    0.41
    స
    0.40
    撼
    0.40
    雱
    0.40
    ל
    0.39
    CH
    0.39
    POSITIVE LOGITS
    >
    0.50
    ->
    0.45
     Loksatta
    0.45
     substantiate
    0.44
     unsub
    0.41
    xlab
    0.40
     expand
    0.40
    ناب
    0.39
    を経て
    0.39
    انب
    0.39
    Act Density 0.001%

    No Known Activations