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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts that are uncommon or obscure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    uncommon or obscure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.37
    تقاوى
    -0.37
    PYX
    -0.30
    KURZBESCHREIBUNG
    -0.29
    ukunft
    -0.28
     Chwiliwch
    -0.28
     ब्रेकडाउन
    -0.28
    createServer
    -0.27
    abstractmethod
    -0.26
    holdet
    -0.26
    POSITIVE LOGITS
     obscure
    0.66
     inconvenient
    0.64
    obscure
    0.60
     convoluted
    0.57
     arcane
    0.54
    convenient
    0.54
    oteric
    0.53
     esoteric
    0.53
    blouse
    0.52
    0.51
    Act Density 0.128%

    No Known Activations