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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures

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

    Punctuations and symbols

    np_acts-logits-general · gemini-2.0-flash

    punctuation and structural markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?=$
    -0.59
    -​
    -0.57
    ]]
    -0.54
    》：
    -0.54
    liesslich
    -0.54
    URDAY
    -0.54
    !»
    -0.53
    /#{
    -0.52
    mapStateToProps
    -0.51
    ：「
    -0.51
    POSITIVE LOGITS
     .
    2.97
     .
    1.40
     .)
    1.32
     .,
    1.26
     ."
    1.22
     .”
    1.13
     .\
    1.08
     .(
    1.08
     .'
    1.06
     ..
    1.04
    Act Density 0.398%

    No Known Activations