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

    Neuronpedia

    INDEX
    Explanations

    design and writing inspiration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Someone
    -0.07
    当前
    -0.07
     designation
    -0.07
     returnValue
    -0.06
     Millionen
    -0.06
     MASK
    -0.06
    islation
    -0.06
     зап
    -0.06
    对应
    -0.06
     by
    -0.06
    POSITIVE LOGITS
     Draw
    0.07
    .velocity
    0.07
    香气
    0.07
    _DROP
    0.07
    handled
    0.07
    got
    0.07
    mia
    0.07
     proceeded
    0.07
     Shade
    0.07
    .UPDATE
    0.07
    Act Density 0.071%

    No Known Activations