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

    Neuronpedia

    INDEX
    Explanations

    references to data tables and figures

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

    tables or figures

    np_acts-logits-general · gemini-2.0-flash

    citations of tables and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.67
    __':
    -0.60
    <eos>
    -0.58
    cario
    -0.53
    的分
    -0.47
    openConnection
    -0.47
     invid
    -0.46
    Wallis
    -0.46
     sla
    -0.45
    __':
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.83
    RegressionTest
    0.78
     couverte
    0.75
     Meksiku
    0.74
     sauvages
    0.72
     supérieures
    0.71
     supérieurs
    0.67
     chimiques
    0.65
     étoit
    0.65
    calaure
    0.65
    Act Density 0.871%

    No Known Activations