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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax and code structure elements

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

    Dim ... as Variant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.87
    лтемелер
    -0.72
     незавершена
    -0.72
     kaarangay
    -0.68
    rungsseite
    -0.66
    AndEndTag
    -0.65
    featureID
    -0.65
     houſe
    -0.65
    IndentedString
    -0.63
    KommentareTeilen
    -0.61
    POSITIVE LOGITS
     extends
    0.67
    <bos>
    0.48
    mtable
    0.47
     is
    0.44
     extend
    0.43
    ene
    0.43
     deal
    0.42
     extended
    0.42
    extends
    0.41
     committed
    0.40
    Act Density 0.001%

    No Known Activations