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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence delimiters

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

    introduction of lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Multiple
    -0.54
    MULTIPLE
    -0.49
     MULTIPLE
    -0.47
     amizade
    -0.45
    pulseira
    -0.44
     desideri
    -0.44
     situation
    -0.43
     adicionales
    -0.43
    multiple
    -0.42
    这件事情
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.61
    SequentialGroup
    0.61
    RenderAtEndOf
    0.59
    ⓧ
    0.58
    0.56
    setVerticalGroup
    0.53
    expandindo
    0.52
    Биография
    0.49
    EDEFAULT
    0.49
     propOrder
    0.49
    Act Density 0.060%

    No Known Activations