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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to data analysis and variables

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

    continuous variables or attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новништво
    -0.49
    WithIOException
    -0.47
    AISSEE
    -0.45
     Gallimard
    -0.42
     ویکی‌پدی
    -0.41
     Administrativna
    -0.40
    forChild
    -0.40
     puff
    -0.38
    urtstag
    -0.37
    orz
    -0.37
    POSITIVE LOGITS
     Continuous
    1.56
    Continuous
    1.53
     continuous
    1.52
    continuous
    1.47
     CONTIN
    1.24
     contín
    1.23
     Contin
    1.23
    CONTIN
    1.20
    Contin
    1.20
     continuously
    1.13
    Act Density 0.035%

    No Known Activations