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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to equations

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

    LaTeX code fragments

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.89
    httphttps
    -0.78
     ?
    -0.72
     [/
    -0.72
    ніципа
    -0.71
     ..."
    -0.71
    таратура
    -0.70
     صوتيه
    -0.70
     Normdatei
    -0.69
     !
    -0.69
    POSITIVE LOGITS
    \
    1.67
    (
    0.92
    {
    0.70
    $
    0.65
    "
    0.65
    &
    0.60
    -
    0.57
    -\
    0.57
    \(
    0.52
    \:
    0.52
    Act Density 0.475%

    No Known Activations