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

    Neuronpedia

    INDEX
    Explanations

    terms related to rarity or exceptional occurrences

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

    occurrence of rare conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.45
    FieldBuilder
    -0.45
    vistar
    -0.44
     nahilalakip
    -0.44
    -------------</
    -0.43
    ilever
    -0.42
    igable
    -0.42
     MainAxisSize
    -0.41
     мәкал
    -0.41
    indrical
    -0.41
    POSITIVE LOGITS
     Rare
    1.59
    Rare
    1.55
     rare
    1.54
     rarest
    1.41
     RARE
    1.34
    rare
    1.34
     rarer
    1.31
     rarity
    1.30
     rares
    1.23
     raro
    1.21
    Act Density 0.010%

    No Known Activations