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

    Neuronpedia

    INDEX
    Explanations

    references to URLs and coding syntax

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

    URLs or code snippets

    np_acts-logits-general · gemini-2.0-flash

    URLs and math problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.63
    stylers
    -0.58
    SaveChangesAsync
    -0.54
    +#+#
    -0.53
    GEBURTSDATUM
    -0.53
    AsUp
    -0.52
    밌
    -0.50
    исленность
    -0.49
     فريبيس
    -0.49
    antaranya
    -0.49
    POSITIVE LOGITS
    Darling
    0.37
    option
    0.36
    Bel
    0.35
    BEL
    0.33
     여
    0.33
    여
    0.33
    groupId
    0.33
     opted
    0.33
     Explanation
    0.32
     informée
    0.32
    Act Density 0.001%

    No Known Activations