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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical formatting and structure in documents

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

    LaTeX environments: align, document

    np_acts-logits-general · gemini-2.0-flash

    ending math environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    forRoot
    -0.63
    stylers
    -0.60
     iprot
    -0.60
    !*\
    -0.58
    |')
    -0.57
    liothèque
    -0.57
    GenerationType
    -0.54
    ,‎
    -0.53
     continúas
    -0.52
    ?',
    -0.51
    POSITIVE LOGITS
    <eos>
    0.81
    IntoConstraints
    0.78
     مشين
    0.78
    __':
    0.75
    ↵↵
    0.74
    __':
    0.65
    __":
    0.65
    hassee
    0.57
     <<<<<<<<<<<<<<
    0.56
    __":
    0.56
    Act Density 0.119%

    No Known Activations