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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and opinion expression

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

    Code or symbols (Q, /*) mixed with English

    np_acts-logits-general · gemini-2.0-flash

    artificial electron

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.64
     समीक्षाएं
    -0.63
    évaluateur
    -0.61
     समीक्षाओं
    -0.60
    HomeAsUpEnabled
    -0.60
     autorytatywna
    -0.58
    たまた
    -0.57
    SourceChecksum
    -0.57
    Примітки
    -0.56
    maxsize
    -0.51
    POSITIVE LOGITS
    NgModule
    0.69
    kháu
    0.65
    ]-->
    0.61
     препратки
    0.61
    HasForeignKey
    0.58
    ']?>
    0.56
    <()>
    0.53
    ανά
    0.53
    }))
    0.52
    лтемелер
    0.51
    Act Density 0.253%

    No Known Activations