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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relations

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

    Mathematical or code-related formulas

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation or math symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.66
     defaultstate
    -0.55
    Derbyniad
    -0.52
     nahilalakip
    -0.51
    这件事情
    -0.50
    mpagne
    -0.49
    WriteTagHelper
    -0.48
    Gizmos
    -0.48
     Fractional
    -0.47
    ->___
    -0.47
    POSITIVE LOGITS
    yntaxException
    0.42
     Friday
    0.37
    rmtree
    0.36
     Pa
    0.36
    etera
    0.35
    oredCriteria
    0.35
     Zeiten
    0.35
     بودن
    0.35
     про
    0.35
     say
    0.35
    Act Density 0.805%

    No Known Activations