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

    Neuronpedia

    INDEX
    Explanations

    sha integrity hashing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vraag
    0.45
    komen
    0.44
     pressed
    0.44
    kommen
    0.40
     polymer
    0.40
     bilo
    0.40
     Spinning
    0.39
    ាក់
    0.39
     Blut
    0.39
     tinggal
    0.39
    POSITIVE LOGITS
    м
    0.48
    л
    0.48
     evaluations
    0.44
    ંડ
    0.42
    дэ
    0.42
    дин
    0.41
     市場
    0.41
     faveur
    0.41
    󠁢
    0.40
     நி
    0.40
    Act Density 0.000%

    No Known Activations