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

    Neuronpedia

    INDEX
    Explanations

    terms related to machine learning dataset processing

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

    (number/group)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.71
    Abitanti
    -0.54
    AndEndTag
    -0.53
    __))
    -0.52
     CascadeType
    -0.50
    TintMode
    -0.49
     ProtoMessage
    -0.49
    -0.49
    makeConstraints
    -0.48
     censiti
    -0.47
    POSITIVE LOGITS
    śmy
    0.48
    FTFY
    0.42
    Handlung
    0.41
    énario
    0.39
     genitori
    0.37
     uñas
    0.36
     jugado
    0.35
    的问道
    0.35
     JL
    0.34
     umana
    0.34
    Act Density 0.002%

    No Known Activations