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

    Neuronpedia

    INDEX
    Explanations

    legacy software/IE8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CLI
    -0.08
    _queries
    -0.07
     seriousness
    -0.07
     learned
    -0.07
     approach
    -0.06
    atform
    -0.06
    464
    -0.06
    ############################
    -0.06
    Form
    -0.06
     innovations
    -0.06
    POSITIVE LOGITS
     UserModel
    0.08
    .EditText
    0.07
     tả
    0.06
    mite
    0.06
     أص
    0.06
    anter
    0.06
     Sprint
    0.06
    (s
    0.06
    ptest
    0.06
     skeletons
    0.06
    Act Density 0.012%

    No Known Activations