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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation marks within the text

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

    the presence of special characters or formatting elements in the text

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

    file names and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clusal
    -0.52
    TSCA
    -0.50
     DMV
    -0.47
    incoming
    -0.47
    saraba
    -0.46
    PreAuthorize
    -0.45
    beak
    -0.45
    koľvek
    -0.45
    ENARIO
    -0.45
    ProcessEvent
    -0.44
    POSITIVE LOGITS
     initComponents
    0.68
    +#+#
    0.65
     GenerationType
    0.65
    msgTypes
    0.57
    mergeFrom
    0.55
     torchvision
    0.53
     paraît
    0.52
    Composable
    0.52
     civili
    0.51
     رسد
    0.51
    Act Density 0.049%

    No Known Activations