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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incons
    -0.07
     Drink
    -0.06
    drink
    -0.06
     babies
    -0.06
     розвит
    -0.06
     Babies
    -0.06
     اسپ
    -0.06
     �
    -0.06
    ante
    -0.06
     Ending
    -0.06
    POSITIVE LOGITS
     Paladin
    0.07
    gregate
    0.07
    사이트
    0.06
    (argv
    0.06
     answering
    0.06
     trochu
    0.06
     خل
    0.06
     subsidi
    0.06
     stratej
    0.06
     suy
    0.06
    Act Density 0.000%

    No Known Activations