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

    Neuronpedia

    INDEX
    Explanations

    expressions related to offering help or support

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

    Following "you," "he," or "we" and a modal verb

    np_acts-logits-general · gemini-2.0-flash

    ability to ask or do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndInit
    -0.52
     bedoeld
    -0.46
     perſon
    -0.45
    rion
    -0.45
     perfons
    -0.44
     ſeveral
    -0.44
     bezoek
    -0.44
     चुनें
    -0.43
    GEBURTS
    -0.43
    nextSibling
    -0.43
    POSITIVE LOGITS
     can
    1.40
    can
    1.13
     could
    1.01
     Can
    1.01
    Can
    1.00
     bisa
    0.96
    could
    0.96
     podemos
    0.95
    我可以
    0.94
    可以
    0.92
    Act Density 0.256%

    No Known Activations