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

    Neuronpedia

    INDEX
    Explanations

    occurrences of structured programming language syntax

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

    Code, code-like, or formal language snippets

    np_acts-logits-general · gemini-2.0-flash

    plurals or Ireland

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nativo
    -0.35
    RenderAtEndOf
    -0.34
    mujer
    -0.29
     inconnu
    -0.29
     Gerente
    -0.28
    ArgsConstructor
    -0.28
     detenido
    -0.27
    principalTable
    -0.27
    AllAfrica
    -0.26
     âme
    -0.26
    POSITIVE LOGITS
    expandindo
    0.68
     Administrativna
    0.67
    Ӕ
    0.61
    脚注の使い方
    0.59
    Chham
    0.59
    mobileqq
    0.59
     gynhyrchwyd
    0.58
    Hentet
    0.57
    0.57
     Italijani
    0.57
    Act Density 0.052%

    No Known Activations