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

    Neuronpedia

    INDEX
    Explanations

    time to double or decay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getFocusAreas
    0.49
     fortalecer
    0.45
     ombil
    0.44
     insertions
    0.44
    菜单
    0.43
    蒌
    0.43
     coordinadora
    0.42
     vín
    0.42
    isVideoRecording
    0.42
     ننوت
    0.41
    POSITIVE LOGITS
     approximate
    0.59
    approx
    0.55
    Approx
    0.53
     approximately
    0.52
     Approximate
    0.48
     approx
    0.48
     ≈
    0.47
     aprox
    0.47
     doubling
    0.46
     roughly
    0.44
    Act Density 0.001%

    No Known Activations