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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "and"

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

    Follows punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    start of entries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     even
    -0.66
     actually
    -0.55
    ,
    -0.54
     then
    -0.51
     as
    -0.49
     never
    -0.49
    ...
    -0.49
     sign
    -0.48
     always
    -0.48
    -
    -0.47
    POSITIVE LOGITS
    出版年
    0.82
     wikipagina
    0.81
    Personensuche
    0.79
    └──
    0.72
     Majefty
    0.70
    
    0.70
     ainfi
    0.69
     AssemblyTitle
    0.68
     plufieurs
    0.67
     betweenstory
    0.66
    Act Density 0.231%

    No Known Activations