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

    Neuronpedia

    INDEX
    Explanations

    formulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sight
    -0.08
     zoo
    -0.07
     zer
    -0.07
     tid
    -0.07
    	sleep
    -0.06
    	sd
    -0.06
     sleep
    -0.06
     achievement
    -0.06
     Hindered
    -0.06
     tiger
    -0.06
    POSITIVE LOGITS
     formula
    0.11
     formulated
    0.11
     formulation
    0.10
    formula
    0.10
     formulate
    0.09
     Formula
    0.08
    ulum
    0.08
    (formData
    0.08
     formulas
    0.08
     Phương
    0.08
    Act Density 0.012%

    No Known Activations