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

    Neuronpedia

    INDEX
    Explanations

    technical or mathematical terms related to programming and equations

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

    after named entities or titles

    np_acts-logits-general · gemini-2.0-flash

    specific dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Theſe
    -1.33
     becauſe
    -1.17
     purpoſe
    -1.14
     houſe
    -1.13
    ſelf
    -1.13
     uſed
    -1.12
     صوتيه
    -1.12
     myſelf
    -1.12
     ―――――
    -1.10
    +#+#
    -1.10
    POSITIVE LOGITS
    <eos>
    0.63
    <bos>
    0.53
    .
    0.47
     in
    0.46
    ↵
    0.43
    ↵↵↵
    0.42
    -
    0.42
     :
    0.42
     de
    0.41
    ,
    0.39
    Act Density 0.655%

    No Known Activations