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

    Neuronpedia

    INDEX
    Explanations

    realism settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clinical
    -0.07
    	cur
    -0.07
     mnoha
    -0.06
    .converter
    -0.06
    covering
    -0.06
    окси
    -0.06
    -history
    -0.06
    drink
    -0.06
    lerinde
    -0.06
    _categorical
    -0.06
    POSITIVE LOGITS
     carte
    0.07
     checkpoints
    0.07
    ротив
    0.06
     Buddh
    0.06
    яти
    0.06
    agne
    0.06
     GBP
    0.06
     gazet
    0.06
    )._
    0.05
    {-#
    0.05
    Act Density 0.001%

    No Known Activations