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

    Neuronpedia

    INDEX
    Explanations

    Ever wonder or notice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sehr
    0.46
     Evidently
    0.45
     매우
    0.45
     Very
    0.44
    とても
    0.44
     psychosis
    0.44
     physicality
    0.42
     verily
    0.42
    非常に
    0.42
     evidentemente
    0.41
    POSITIVE LOGITS
     wondered
    1.23
     wondering
    1.15
     wonder
    1.11
     struggle
    1.00
    wonder
    1.00
     struggled
    0.95
     Wonder
    0.88
     dread
    0.87
     Struggle
    0.86
    Wonder
    0.86
    Act Density 0.020%

    No Known Activations