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

    Neuronpedia

    INDEX
    Explanations

    specific keywords related to data, programming, and technology

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

    Tokens followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    words ending in 'e' followed by numbers or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ness
    -1.49
    nya
    -1.34
    name
    -0.96
    sy
    -0.83
    d
    -0.81
    sa
    -0.80
    not
    -0.80
    night
    -0.80
    so
    -0.79
    了
    -0.78
    POSITIVE LOGITS
    e
    0.58
    eeee
    0.57
    eeeeeeee
    0.54
    eeeee
    0.50
    eee
    0.49
    eeeeee
    0.45
    ee
    0.44
     mergeFrom
    0.41
    lectron
    0.40
    lets
    0.40
    Act Density 2.058%

    No Known Activations