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

    Neuronpedia

    INDEX
    Explanations

    terms related to urban and technical concepts

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

    after short abbreviations

    np_acts-logits-general · gemini-2.0-flash

    code abbreviations and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.74
     itſelf
    -0.74
     $_(
    -0.68
     purpoſe
    -0.66
     pleaſure
    -0.66
    TagMode
    -0.66
     queſta
    -0.65
     $_"
    -0.64
     strconv
    -0.63
     Geiſt
    -0.63
    POSITIVE LOGITS
    hydrop
    0.39
    datab
    0.39
    icec
    0.37
     redb
    0.36
     Lights
    0.35
    datat
    0.35
     McN
    0.35
    Overs
    0.34
    icep
    0.34
     Quicks
    0.34
    Act Density 1.505%

    No Known Activations