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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or sentence boundaries

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

    domain names and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portály
    -0.62
     AssemblyTitle
    -0.61
    arangay
    -0.59
    hoeddwyd
    -0.57
    Portail
    -0.54
     autorytatywna
    -0.54
     kasarigan
    -0.53
     sánchez
    -0.52
    awtextra
    -0.51
    complexContent
    -0.50
    POSITIVE LOGITS
    .
    0.46
    IndentedString
    0.40
    pom
    0.38
     Doctor
    0.37
    انجليز
    0.37
    +#+#
    0.36
     Beta
    0.36
    sti
    0.36
    fan
    0.35
     OSI
    0.35
    Act Density 0.028%

    No Known Activations