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

    Neuronpedia

    INDEX
    Explanations

    OpenID, DeepMind, TensorFlow, WireGuard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    APPLE
    0.41
    itabbam
    0.41
    powerful
    0.40
     STADT
    0.40
    ongoing
    0.40
    either
    0.39
    欝
    0.39
     BRCA
    0.38
     Reglamento
    0.38
    NATIONAL
    0.38
    POSITIVE LOGITS
    View
    0.50
    Dict
    0.46
    Flow
    0.43
    Fi
    0.42
    Sphere
    0.42
    Stream
    0.41
    Drive
    0.41
    Drop
    0.40
    Vie
    0.40
    Plus
    0.40
    Act Density 0.141%

    No Known Activations