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

    Neuronpedia

    INDEX
    Explanations

    code syntax and operators in programming-related texts

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

    code and math syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.52
     ligiloj
    -0.49
    /*-
    -0.48
    Autoritní
    -0.48
     plebis
    -0.46
     kohdetta
    -0.46
    migrationBuilder
    -0.45
    optarg
    -0.43
     labours
    -0.42
     BoxFit
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.62
     söyl
    0.52
     omtrent
    0.50
     referência
    0.49
     raiſ
    0.48
     adresu
    0.48
     approximately
    0.47
     adelantado
    0.47
     öppna
    0.46
    approximately
    0.45
    Act Density 0.043%

    No Known Activations