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

    Neuronpedia

    INDEX
    Explanations

    references to scientific research papers and their associated metadata

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

    Numbers within parentheses

    np_acts-logits-general · gemini-2.0-flash

    citation numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.82
     AssemblyVersion
    -0.75
    setVerticalGroup
    -0.66
    Vidite
    -0.66
     nahilalakip
    -0.65
    Portály
    -0.65
    Rptr
    -0.64
    maría
    -0.63
    RefNanny
    -0.63
    protoimpl
    -0.62
    POSITIVE LOGITS
     heureuse
    0.44
     pokok
    0.43
    ::::::::
    0.43
    ícil
    0.43
     Tuff
    0.43
    abstractmethod
    0.42
    0.41
     présidentielle
    0.41
    fastjson
    0.41
     vraag
    0.41
    Act Density 0.102%

    No Known Activations