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

    Neuronpedia

    INDEX
    Explanations

    references to specific people, tutorials, or educational materials

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

    Tokens appearing before numbers

    np_acts-logits-general · gemini-2.0-flash

    books and educational resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anjutnya
    -0.31
     despacho
    -0.29
     penerima
    -0.29
     Kriegs
    -0.28
    цезда
    -0.27
     detención
    -0.27
     deductions
    -0.25
     unload
    -0.25
     matahari
    -0.25
     Staates
    -0.24
    POSITIVE LOGITS
     betweenstory
    1.05
    RegressionTest
    0.95
     disambiguazione
    0.89
    +#+
    0.88
    ########.
    0.88
    ⓧ
    0.85
    atguigu
    0.82
    transQ
    0.82
    RTEE
    0.80
    MessageOf
    0.79
    Act Density 0.670%

    No Known Activations