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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and terms related to electronic devices

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

    Follows punctuation or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    numbers, symbols, and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     !!!
    -0.61
    …..
    -0.60
     …..
    -0.58
    …….
    -0.57
     I
    -0.56
    ….
    -0.55
    ………
    -0.54
    maktadır
    -0.53
    !!!
    -0.53
     Wikipedia
    -0.52
    POSITIVE LOGITS
    دانشنامهٔ
    0.73
     houſe
    0.70
     Houſe
    0.69
     beſt
    0.68
     iStock
    0.67
     stepmother
    0.65
    URLException
    0.65
     Anſ
    0.65
     allarg
    0.65
     BufferedWriter
    0.64
    Act Density 0.201%

    No Known Activations