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

    Neuronpedia

    INDEX
    Explanations

    high monetary values and figures

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

    dollar amounts and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     common
    -0.44
     négo
    -0.42
     available
    -0.41
    ارم
    -0.41
     db
    -0.40
    жное
    -0.40
     full
    -0.40
     
    -0.39
     connection
    -0.39
     w
    -0.39
    POSITIVE LOGITS
    RegressionTest
    0.75
     ſche
    0.71
     betweenstory
    0.71
     AssemblyVersion
    0.71
    AISSEE
    0.69
     ویکی‌پدیای
    0.68
     Numerade
    0.67
     nonUne
    0.66
     nakalista
    0.65
     Normdatei
    0.65
    Act Density 0.090%

    No Known Activations