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

    Neuronpedia

    INDEX
    Explanations

    terms related to characteristic traits and descriptions of objects or phenomena

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

    characterize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Awards
    -0.28
    liquez
    -0.28
    Penulis
    -0.28
     Hons
    -0.27
     compar
    -0.27
    écnicas
    -0.26
    obacz
    -0.26
     angekommen
    -0.25
     hon
    -0.25
     inte
    -0.25
    POSITIVE LOGITS
     فريبيس
    0.86
    expandindo
    0.81
    AndEndTag
    0.77
     disambiguazione
    0.74
    SourceChecksum
    0.70
     Infórmanos
    0.67
    adaptiveStyles
    0.67
    StructEnd
    0.67
    IndentedString
    0.66
     Италијани
    0.66
    Act Density 0.197%

    No Known Activations