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

    Neuronpedia

    INDEX
    Explanations

    coding/math operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :)↵
    -0.07
    !")↵
    -0.07
     ethnic
    -0.07
     --↵
    -0.07
     Hutch
    -0.07
    ]);↵
    -0.06
    eggies
    -0.06
    "]),↵
    -0.06
    ()));↵
    -0.06
     violet
    -0.06
    POSITIVE LOGITS
     lasc
    0.06
    쪽
    0.06
    IBUT
    0.06
    iquer
    0.06
    heits
    0.06
     gruesome
    0.06
     insider
    0.06
    .PrintWriter
    0.06
    iqué
    0.06
    	string
    0.06
    Act Density 0.052%

    No Known Activations