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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.81
     was
    -0.64
     is
    -0.61
    PhysRevD
    -0.61
     dévelo
    -0.57
    didReceive
    -0.57
     braccia
    -0.57
     tromper
    -0.57
    izione
    -0.56
    fillType
    -0.56
    POSITIVE LOGITS
     arrive
    0.62
    SceneManagement
    0.59
     appear
    0.56
     exist
    0.56
     deserve
    0.55
     remain
    0.55
    }],
    0.54
     consist
    0.53
     involve
    0.52
     available
    0.50
    Act Density 0.009%

    No Known Activations