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

    Neuronpedia

    INDEX
    Explanations

    instances of class definitions in code

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

    class followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.57
     Савезне
    -0.56
     llorar
    -0.50
     protoimpl
    -0.49
    SequentialGroup
    -0.47
    horabuena
    -0.45
     iNdEx
    -0.45
    下载附件
    -0.44
     ivelany
    -0.44
     <>",
    -0.43
    POSITIVE LOGITS
    class
    1.28
     class
    1.23
     Class
    1.02
    Class
    0.92
     classe
    0.84
     CLASS
    0.79
     classes
    0.77
     Klasse
    0.73
    classe
    0.72
     kelas
    0.71
    Act Density 0.007%

    No Known Activations