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

    Neuronpedia

    INDEX
    Explanations

    personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igel
    -0.07
    igroup
    -0.07
    (TRUE
    -0.06
     acknow
    -0.06
     soll
    -0.06
    kır
    -0.06
     �
    -0.06
    acam
    -0.06
     rites
    -0.06
     Comput
    -0.06
    POSITIVE LOGITS
    	register
    0.07
     ENV
    0.06
     Savage
    0.06
    /problems
    0.06
     tématu
    0.06
     projector
    0.06
    Env
    0.06
    Crud
    0.06
     plagued
    0.06
     Ellison
    0.06
    Act Density 0.003%

    No Known Activations