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

    Neuronpedia

    INDEX
    Explanations

    é

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	elem
    -0.07
    undreds
    -0.07
    Michelle
    -0.07
     onStart
    -0.07
     familia
    -0.06
     Finish
    -0.06
    IDGE
    -0.06
    eten
    -0.06
    	idx
    -0.06
    43
    -0.06
    POSITIVE LOGITS
    ?!↵↵
    0.07
    ?t
    0.06
    746
    0.06
     vampire
    0.06
    。不
    0.06
     चल
    0.06
     €
    0.06
     Kaw
    0.06
    lear
    0.06
     Кри
    0.06
    Act Density 0.007%

    No Known Activations