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

    Neuronpedia

    INDEX
    Explanations

    phrases that quantify the quantity or magnitude of something

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

    amount of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BA
    -0.44
     BAU
    -0.42
     ویکی‌پدی
    -0.41
    oughs
    -0.41
     Whelan
    -0.40
    autogui
    -0.40
    BAU
    -0.39
    BA
    -0.39
    Portail
    -0.38
     Bau
    -0.38
    POSITIVE LOGITS
    expandindo
    0.67
     Administrativna
    0.60
     raiſ
    0.57
     itſelf
    0.56
     betweenstory
    0.56
    transQ
    0.55
     encre
    0.54
     fubject
    0.53
     tranſ
    0.52
     Signalez
    0.49
    Act Density 0.063%

    No Known Activations