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

    Neuronpedia

    INDEX
    Explanations

    specific transitions in mathematical models or expressions

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

    Months and years indicators

    np_acts-logits-general · gemini-2.0-flash

    year and citation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.92
    ']))
    -0.79
     Мексичка
    -0.77
    ]))
    -0.70
    />";
    -0.68
    AsUp
    -0.65
    CompilerServices
    -0.65
    >`;
    -0.65
    ')";
    -0.64
    ciples
    -0.64
    POSITIVE LOGITS
     २०
    0.54
    EndOf
    0.54
    ソ
    0.51
    2
    0.49
     Tahun
    0.48
    Year
    0.47
     Años
    0.44
    ImageContext
    0.44
     manqué
    0.44
     año
    0.44
    Act Density 0.142%

    No Known Activations