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

    Neuronpedia

    INDEX
    Explanations

    patterns and syntax related to regular expressions

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

    `+`.]*`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.83
    CloseOperation
    -0.74
    awtextra
    -0.72
    <unused28>
    -0.71
    <unused68>
    -0.71
    <unused8>
    -0.71
    <unused42>
    -0.71
    <unused74>
    -0.71
    [@BOS@]
    -0.71
    <unused3>
    -0.71
    POSITIVE LOGITS
     tertentu
    0.36
     ilang
    0.35
     Raub
    0.34
     Longo
    0.34
    .
    0.33
    leten
    0.33
     Monats
    0.32
    迎え
    0.32
     rasgos
    0.32
     eventualmente
    0.32
    Act Density 0.014%

    No Known Activations