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

    Neuronpedia

    INDEX
    Explanations

    exploring software and positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝜌
    0.43
    Generator
    0.41
    𝖽
    0.40
    Dougall
    0.38
    涌
    0.38
    AKES
    0.38
    ᚗ
    0.38
     ಹೇ
    0.37
    Marne
    0.37
    𝘈
    0.37
    POSITIVE LOGITS
     plans
    0.43
    fxml
    0.42
     super
    0.41
     desire
    0.40
     controllers
    0.40
     controller
    0.39
    RestController
    0.39
     Ctrl
    0.38
     L
    0.38
    htmlspecialchars
    0.38
    Act Density 0.001%

    No Known Activations