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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names of individuals

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

    names followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     față
    -0.28
     olmayan
    -0.28
    wpi
    -0.26
     lifted
    -0.26
     chi̍t
    -0.25
    telse
    -0.25
     cơ
    -0.24
     defen
    -0.24
    BOURNE
    -0.24
    addColumn
    -0.23
    POSITIVE LOGITS
    Datuak
    0.78
     препратки
    0.76
    Autoritní
    0.70
    makeText
    0.62
     bezeichneter
    0.60
    AndEndTag
    0.60
    ьаж
    0.59
     nakalista
    0.58
     deſſen
    0.57
    RenderAtEndOf
    0.57
    Act Density 0.030%

    No Known Activations