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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurement-related expressions in mathematical or scientific contexts

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

    1 mm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     printed
    -0.46
     vork
    -0.39
     binding
    -0.38
    êmica
    -0.38
     heads
    -0.37
     vacuum
    -0.37
     surpresa
    -0.37
     promise
    -0.37
     Hanley
    -0.36
     fishing
    -0.36
    POSITIVE LOGITS
     OMITBAD
    0.68
     ویکی‌پدی
    0.59
    出版年
    0.57
     EconPapers
    0.56
     autorytatywna
    0.55
    SequentialGroup
    0.54
    __":
    0.50
    ⎩
    0.50
    };*/
    0.49
     <<<<<<<<<<<<<<
    0.48
    Act Density 0.961%

    No Known Activations