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

    Neuronpedia

    INDEX
    Explanations

    chess strategy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حدث
    -0.08
     Jackpot
    -0.08
    _hresult
    -0.08
    _Category
    -0.08
     Studi
    -0.08
     восп
    -0.08
     произош
    -0.07
    经历
    -0.07
    พบ
    -0.07
     chế
    -0.07
    POSITIVE LOGITS
     squares
    0.10
     threats
    0.10
     Humph
    0.09
     aggressive
    0.09
     cubes
    0.09
     knights
    0.09
     attacking
    0.09
     threatened
    0.09
     castles
    0.09
     troops
    0.09
    Act Density 0.005%

    No Known Activations