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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fake
    -0.07
     Rich
    -0.06
    /includes
    -0.06
     queens
    -0.06
    .comp
    -0.06
     informative
    -0.06
    息
    -0.05
    	K
    -0.05
     facade
    -0.05
    朱
    -0.05
    POSITIVE LOGITS
    .slf
    0.06
    omencl
    0.06
     correspondence
    0.06
     связ
    0.06
     conna
    0.06
     cardio
    0.06
     employing
    0.06
     genera
    0.06
     daar
    0.06
     inspect
    0.06
    Act Density 0.001%

    No Known Activations