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

    Neuronpedia

    INDEX
    Explanations

    om

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spot
    -0.07
    เมน
    -0.07
    געת
    -0.07
    备战
    -0.07
    =label
    -0.06
    辅导
    -0.06
     makeover
    -0.06
    半年
    -0.06
    ssue
    -0.06
    닝
    -0.06
    POSITIVE LOGITS
    	form
    0.07
    ctions
    0.07
    ikt
    0.07
     Cro
    0.07
     Rutgers
    0.07
    .FirstOrDefault
    0.07
    /to
    0.07
     Appears
    0.07
    0.07
    .DateTimeField
    0.07
    Act Density 0.001%

    No Known Activations