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

    Neuronpedia

    INDEX
    Explanations

    standard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    サ
    -0.08
     const
    -0.07
    England
    -0.07
    	override
    -0.06
    building
    -0.06
    handling
    -0.06
     оттен
    -0.06
     galer
    -0.06
    	Player
    -0.06
    unless
    -0.06
    POSITIVE LOGITS
     familial
    0.07
    -ce
    0.07
     sâu
    0.06
    _IMPORT
    0.06
    *)↵↵
    0.06
    ichert
    0.06
     وف
    0.06
    ayne
    0.06
    _strategy
    0.06
     ((_
    0.06
    Act Density 0.002%

    No Known Activations