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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating ability or possibility

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

    cannot do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.52
    SerializeField
    -0.44
    fxml
    -0.43
     disponibilités
    -0.42
    jsxFileName
    -0.42
     opportunity
    -0.40
     messing
    -0.40
     option
    -0.40
     habit
    -0.40
     facult
    -0.40
    POSITIVE LOGITS
     Cannot
    0.76
    Cannot
    0.74
    Impossible
    0.65
     cannot
    0.64
     impossibile
    0.62
     Impossible
    0.60
    cannot
    0.60
     impossível
    0.59
     CANNOT
    0.59
    impossible
    0.56
    Act Density 0.019%

    No Known Activations