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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eden
    -0.07
    Specifications
    -0.06
     shelter
    -0.06
     oil
    -0.06
     далеко
    -0.06
     Βα
    -0.06
     Halo
    -0.06
    助
    -0.06
     Spoj
    -0.06
    fuck
    -0.06
    POSITIVE LOGITS
     quart
    0.07
     şar
    0.07
    净
    0.06
    %=
    0.06
    ิทย
    0.06
    ण
    0.06
    	font
    0.06
     bins
    0.06
     quỹ
    0.06
    	component
    0.06
    Act Density 0.005%

    No Known Activations