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

    Neuronpedia

    INDEX
    Explanations

    quick jobs and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ڑ
    0.53
    dipl
    0.44
    acheter
    0.44
    ੁ
    0.44
    भिन्न
    0.43
    老師
    0.42
    話題
    0.42
    bure
    0.42
    𝖺
    0.41
     protagonists
    0.40
    POSITIVE LOGITS
    Tensor
    0.45
     ionized
    0.44
     infrequent
    0.41
     conditioned
    0.41
    Entry
    0.41
    RequestParam
    0.40
     compressed
    0.40
    Aging
    0.40
    Sequence
    0.39
     compaction
    0.39
    Act Density 0.005%

    No Known Activations