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

    Neuronpedia

    INDEX
    Explanations

    Over-the-counter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    382
    -0.08
     practice
    -0.08
    Practice
    -0.08
    381
    -0.07
    303
    -0.07
    ตัว
    -0.07
    Regular
    -0.07
    Observe
    -0.07
    _regular
    -0.07
    Dive
    -0.07
    POSITIVE LOGITS
     {{↵
    0.09
     соответственно
    0.08
     дети
    0.08
    ONO
    0.08
     Fabric
    0.08
     уничтож
    0.08
     logisch
    0.08
     slain
    0.08
     kunder
    0.08
     bevel
    0.08
    Act Density 0.008%

    No Known Activations