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

    Neuronpedia

    INDEX
    Explanations

    life cycle stages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (""))
    -0.07
    JSGlobalScope
    -0.07
     School
    -0.07
     Lo
    -0.06
    Geo
    -0.06
    前不久
    -0.06
     ONE
    -0.06
    	String
    -0.06
     staggering
    -0.06
    Không
    -0.06
    POSITIVE LOGITS
    坛
    0.08
    閱
    0.08
    议会
    0.07
    _foot
    0.07
    ❧
    0.06
    ieval
    0.06
    口味
    0.06
     Smash
    0.06
     ingl
    0.06
    尊严
    0.06
    Act Density 0.068%

    No Known Activations