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

    Neuronpedia

    INDEX
    Explanations

    occurrences of periods, indicating the end of sentences

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

    javascript method names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.59
    AddTagHelper
    -0.57
     juſ
    -0.56
    AccessorTable
    -0.52
    basicConfig
    -0.51
     itſelf
    -0.51
     totalCount
    -0.50
    EndContext
    -0.50
     maxHeight
    -0.50
    IntoConstraints
    -0.49
    POSITIVE LOGITS
    <bos>
    0.55
    ⓘ
    0.53
    .
    0.52
    >().
    0.49
     favorite
    0.49
    WriteLiteral
    0.49
    Portale
    0.48
     Benn
    0.48
    >::
    0.47
     "
    0.47
    Act Density 0.001%

    No Known Activations