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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in the form of semicolons

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

    code delimiters and empty strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    roto
    -0.50
    omnia
    -0.49
    <eos>
    -0.47
     not
    -0.47
    warts
    -0.46
    OrBuilder
    -0.46
    more
    -0.46
    usia
    -0.45
    ULES
    -0.44
    tru
    -0.43
    POSITIVE LOGITS
    Hochspringen
    0.82
    GenerationType
    0.77
     jScrollPane
    0.76
     nahilalakip
    0.74
     Wikimedijinoj
    0.69
     ModelExpression
    0.69
    ########.
    0.68
     localObject
    0.67
    WebVitals
    0.66
     CreateTagHelper
    0.65
    Act Density 0.028%

    No Known Activations