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

    Neuronpedia

    INDEX
    Explanations

    statistical or mathematical relationships and expressions in a scientific context

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

    Measurements, quantities, or diagrams

    np_acts-logits-general · gemini-2.0-flash

    numbers, diagrams, or figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.88
    +#+#
    -0.67
    rungsseite
    -0.64
    AndEndTag
    -0.62
    #+#
    -0.61
    migrationBuilder
    -0.59
    endpush
    -0.58
     صوتيه
    -0.57
    ロウィン
    -0.56
     dezelve
    -0.55
    POSITIVE LOGITS
     Picture
    0.44
     Figure
    0.42
     picture
    0.41
     pictures
    0.36
     Pictures
    0.36
    Picture
    0.35
    ↵↵↵
    0.35
     Schematic
    0.34
    ↵
    0.34
    ↵↵
    0.34
    Act Density 0.302%

    No Known Activations