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

    Neuronpedia

    INDEX
    Explanations

    appearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	vector
    -0.07
     Js
    -0.07
    OBJECT
    -0.07
    (domain
    -0.07
    	result
    -0.07
     overwrite
    -0.06
     slit
    -0.06
     zat
    -0.06
    slt
    -0.06
     frat
    -0.06
    POSITIVE LOGITS
     appearance
    0.09
     appearances
    0.08
     assistir
    0.07
     Appearance
    0.07
    出现
    0.07
    ように
    0.07
     gerçekten
    0.07
     complexion
    0.07
     surfaces
    0.07
    现
    0.07
    Act Density 0.010%

    No Known Activations