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

    Neuronpedia

    INDEX
    Explanations

    statistical significance and comparisons between groups

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

    no, not, cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.66
    EDEFAULT
    -0.54
    却
    -0.46
    دانشنامهٔ
    -0.46
    却是
    -0.45
    تفصیلات
    -0.45
    however
    -0.43
     THOUGH
    -0.43
     خارجية
    -0.42
    けどね
    -0.42
    POSITIVE LOGITS
     pouvoit
    0.44
     even
    0.43
     disso
    0.43
    віть
    0.40
     persino
    0.40
     nawet
    0.39
     Syrie
    0.39
    enment
    0.39
     withal
    0.39
     quidem
    0.39
    Act Density 0.286%

    No Known Activations