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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structure, particularly around defining and running methods in a programming language

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    structured formatting or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -1.18
     виправивши
    -1.17
     EconPapers
    -1.16
    Diweddarwch
    -1.10
    setVerticalGroup
    -1.05
    expandindo
    -1.04
     Roskov
    -1.03
    principalTable
    -0.93
    InvalidProtocol
    -0.89
     '\\;'
    -0.89
    POSITIVE LOGITS
    </em>
    1.00
    </i>
    0.88
    </u>
    0.69
    </h5>
    0.54
    </h2>
    0.49
    </h6>
    0.44
    substack
    0.41
     怎样
    0.40
    ↵
    0.39
     tantôt
    0.39
    Act Density 0.272%

    No Known Activations