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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their related quantities in the text

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

    Numbers followed by units of measurement

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lèvres
    -0.81
     enfans
    -0.78
     dieux
    -0.76
     vœux
    -0.74
     varandra
    -0.74
     épaules
    -0.74
     âmes
    -0.71
     prêtres
    -0.71
     étoient
    -0.71
     oreilles
    -0.70
    POSITIVE LOGITS
     or
    0.97
     million
    0.75
     gaz
    0.68
     maybe
    0.68
     fucking
    0.68
     billion
    0.67
     damn
    0.66
     guys
    0.65
     hours
    0.65
     minutes
    0.64
    Act Density 0.335%

    No Known Activations