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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific formatting or metadata indicators in a technical context

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

    Preceding a question, summary, or introduction

    np_acts-logits-general · gemini-2.0-flash

    circuit, Q, same, introduction, summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ality
    -0.46
    мання
    -0.46
     تانيه
    -0.46
    velles
    -0.43
     commerciali
    -0.43
    колад
    -0.43
     relation
    -0.42
    lüğ
    -0.42
     kohdetta
    -0.42
    источник
    -0.42
    POSITIVE LOGITS
     виправивши
    0.71
    rungsseite
    0.70
    ArgsConstructor
    0.67
    awtextra
    0.65
    Biographie
    0.65
     NSCoder
    0.64
    exitRule
    0.63
    ngdoc
    0.62
    __*/
    0.62
     scorers
    0.61
    Act Density 0.302%

    No Known Activations