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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yog
    -0.07
     spike
    -0.07
    .Xtra
    -0.07
    (Core
    -0.06
    _SHORT
    -0.06
    Pretty
    -0.06
     hè
    -0.06
     tyto
    -0.06
     knih
    -0.06
     Civilization
    -0.06
    POSITIVE LOGITS
     Он
    0.07
    	rc
    0.07
     �
    0.06
     apr
    0.06
    いや
    0.06
    １０
    0.06
    督
    0.06
    ัฒน
    0.06
    =edge
    0.06
    	RTHOOK
    0.06
    Act Density 0.019%

    No Known Activations