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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions of ability or potential

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

    Ability or permission to do something

    np_acts-logits-general · gemini-2.0-flash

    able to easily perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vouloir
    -0.65
     want
    -0.64
     Want
    -0.63
     étoit
    -0.61
    want
    -0.59
    Want
    -0.58
     need
    -0.57
     wanting
    -0.52
     auroit
    -0.52
    need
    -0.52
    POSITIVE LOGITS
     easily
    1.30
    easily
    1.06
     freely
    1.02
     readily
    0.98
     Easily
    0.98
     comfortably
    0.98
     facilement
    0.98
    Easily
    0.94
     facilmente
    0.92
     safely
    0.90
    Act Density 0.333%

    No Known Activations