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

    Neuronpedia

    INDEX
    Explanations

    special characters and whitespace patterns

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

    Tokens after newlines, often related to closing statements

    np_acts-logits-general · gemini-2.0-flash

    code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jupiter
    -0.47
    ]])
    -0.40
    --}}
    -0.39
    ⎨
    -0.38
    }}
    -0.38
    </blockquote>
    -0.37
    very
    -0.37
    </strong>
    -0.37
    ​
    -0.36
    )"),
    -0.36
    POSITIVE LOGITS
    IntoConstraints
    0.91
    LookAnd
    0.72
     betweenstory
    0.70
    UserScript
    0.68
    AsUp
    0.64
     فريبيس
    0.61
    ſammen
    0.60
     AssemblyCulture
    0.59
    دانشنامهٔ
    0.58
     computation
    0.58
    Act Density 0.765%

    No Known Activations