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

    Neuronpedia

    INDEX
    Explanations

    specific numerical or statistical representations within text

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

    Follows questions or technical terms

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    -0.77
     ‘
    -0.72
    ”
    -0.72
     ens
    -0.66
    ’
    -0.66
    ing
    -0.66
    ません
    -0.61
    …………………………………………
    -0.61
    rån
    -0.60
    baya
    -0.60
    POSITIVE LOGITS
    --}}
    0.79
    0.79
    mallows
    0.79
     Saltar
    0.79
    -~
    0.77
    enumii
    0.76
    felves
    0.76
     photolibrary
    0.75
    awtextra
    0.74
     ◦
    0.74
    Act Density 0.141%

    No Known Activations