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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the action of turning something on or off

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

    turning on or activating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GUILayout
    -0.46
     незавершена
    -0.44
    creativecommons
    -0.38
     attempt
    -0.38
     esfuerzo
    -0.38
     ieg
    -0.37
    fxml
    -0.36
    ierende
    -0.36
     effort
    -0.35
     endeavours
    -0.35
    POSITIVE LOGITS
    IntoConstraints
    0.76
     Monfieur
    0.64
     activate
    0.62
     encender
    0.61
     activated
    0.60
     igång
    0.60
     Efq
    0.59
     SwitchCompat
    0.59
     Activate
    0.56
    Carcinogenicity
    0.56
    Act Density 0.006%

    No Known Activations