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

    Neuronpedia

    INDEX
    Explanations

    ratios and mixtures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     work
    -0.08
    	work
    -0.08
     UIApplication
    -0.08
     underst
    -0.08
     bekommen
    -0.08
    Work
    -0.07
     Work
    -0.07
    werk
    -0.07
     equipped
    -0.07
    work
    -0.07
    POSITIVE LOGITS
    比例
    0.12
     proportions
    0.11
     blended
    0.10
     mixture
    0.10
     ингреди
    0.10
    _fraction
    0.10
     blending
    0.09
     proportion
    0.09
     смесь
    0.09
     mixtures
    0.09
    Act Density 0.015%

    No Known Activations