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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to technical specifications and methods

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

    preceding "runoff", negative adjectives, and words before "solution"

    np_acts-logits-general · gemini-2.0-flash

    phrases or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.50
    ,
    -0.48
    ↵↵
    -0.48
     
    -0.46
    </blockquote>
    -0.45
    </em>
    -0.45
    :
    -0.45
    ↵
    -0.43
    </i>
    -0.42
    <unused63>
    -0.39
    POSITIVE LOGITS
    LookAnd
    1.29
     defaultstate
    1.27
    FunctionFlags
    1.22
    Personendaten
    1.18
     AssemblyCulture
    1.13
     kasarigan
    1.11
    ьаж
    1.09
    bootstrapcdn
    1.07
    AddHtmlAttribute
    1.06
     beginnetje
    1.05
    Act Density 1.134%

    No Known Activations