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

    Neuronpedia

    INDEX
    Explanations

    strategy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dollar
    -0.07
     Coca
    -0.07
     Colon
    -0.07
    ор
    -0.07
     flushing
    -0.06
    accounts
    -0.06
    magnitude
    -0.06
    toi
    -0.06
    ुलन
    -0.06
     Yok
    -0.06
    POSITIVE LOGITS
     strategies
    0.08
     strategy
    0.08
     최
    0.07
    	item
    0.06
    剩
    0.06
     Strategy
    0.06
    Aw
    0.06
     全
    0.06
    (cells
    0.06
    ufficient
    0.06
    Act Density 0.015%

    No Known Activations