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

    Neuronpedia

    INDEX
    Explanations

    references to the term "shallow" in various contexts

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

    shallow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Notae
    -0.50
     {*}
    -0.45
    logrus
    -0.44
    ProcessEvent
    -0.43
     getOrder
    -0.43
     EventType
    -0.42
    CURLOPT
    -0.42
     getNumber
    -0.42
    ActionEvent
    -0.41
     kirja
    -0.41
    POSITIVE LOGITS
     Shallow
    2.00
     shallow
    1.98
    shallow
    1.94
    Shallow
    1.92
     shallo
    1.30
    浅
    1.23
    淺
    1.07
     浅
    1.05
    얕
    0.86
     superficial
    0.79
    Act Density 0.003%

    No Known Activations