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

    Neuronpedia

    INDEX
    Explanations

    particles or components referenced in comparisons or ratings

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

    highest, lowest, fraction, number, loss, winning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.61
    ContainerState
    -0.55
    URLException
    -0.55
     betweenstory
    -0.54
     getItemCount
    -0.53
    FileChooser
    -0.51
     utafitiHapana
    -0.51
     Wicidata
    -0.51
     bluz
    -0.50
    ThemeOverlay
    -0.49
    POSITIVE LOGITS
     Italijani
    0.43
    substack
    0.36
    次
    0.34
     multi
    0.34
    endsection
    0.33
    formKey
    0.32
    ouwd
    0.31
    }}^
    0.31
     dreamt
    0.31
    readAs
    0.30
    Act Density 0.115%

    No Known Activations