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

    Neuronpedia

    INDEX
    Explanations

    technical terms and jargon related to specific scientific fields

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

    ending with suffixes like "-ans", "-ines", "-ing", or "-als"

    np_acts-logits-general · gemini-2.0-flash

    biological suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.85
     "
    -0.81
    ,
    -0.79
     (
    -0.79
    '
    -0.70
    ↵↵
    -0.68
    /
    -0.67
    2
    -0.67
    .
    -0.66
    :
    -0.65
    POSITIVE LOGITS
     للمعارف
    1.18
    ]")]
    1.17
    DockStyle
    1.16
    aarrggbb
    1.15
     تانيه
    1.09
     ujednoznacz
    1.03
     myſelf
    1.02
     ſind
    1.01
     Efq
    1.00
    ſelf
    0.99
    Act Density 0.950%

    No Known Activations