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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EventEmitter
    -0.08
     yönetim
    -0.07
     Costco
    -0.06
     policym
    -0.06
     gum
    -0.06
     nebezpeč
    -0.06
     TEM
    -0.06
    Previous
    -0.06
     insanity
    -0.06
    .IN
    -0.06
    POSITIVE LOGITS
    -as
    0.07
     values
    0.06
     свят
    0.06
    	I
    0.06
    -fly
    0.06
    (train
    0.06
     outset
    0.06
    rug
    0.06
     항
    0.06
    _comp
    0.06
    Act Density 0.000%

    No Known Activations