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

    Neuronpedia

    INDEX
    Explanations

    descriptive metadata related to visual media

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

    Filename extensions and URLs

    np_acts-logits-general · gemini-2.0-flash

    URLs and JSON separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     …)
    -0.67
    --]
    -0.64
     ...)
    -0.61
    …).
    -0.56
     ...]
    -0.53
    %]
    -0.52
    $).
    -0.50
    ?).
    -0.50
     bit
    -0.49
    /]
    -0.49
    POSITIVE LOGITS
    ","
    1.71
    ','
    1.65
    ">'+
    1.54
    "+"
    1.50
     "+
    1.48
    "+
    1.43
     '+
    1.35
    '+
    1.31
     ","
    1.30
     "+"
    1.28
    Act Density 0.232%

    No Known Activations