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

    Neuronpedia

    INDEX
    Explanations

    instances of potential or conditional language

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

    Follows "Q" or a period

    np_acts-logits-general · gemini-2.0-flash

    nevertheless, nonetheless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.68
     estimés
    -0.67
     but
    -0.60
    enumi
    -0.53
    GraphicsUnit
    -0.52
    tagHelperRunner
    -0.52
    のですが
    -0.51
    Aktualisiert
    -0.48
     αλλά
    -0.48
    もありますが
    -0.47
    POSITIVE LOGITS
     nonetheless
    1.52
     nevertheless
    1.36
     ändå
    1.08
    etheless
    1.07
     néanmoins
    0.95
     dennoch
    0.94
    Nonetheless
    0.92
     trotzdem
    0.87
     immerhin
    0.83
    それでも
    0.82
    Act Density 0.412%

    No Known Activations