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

    Neuronpedia

    INDEX
    Explanations

    der

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Without
    -0.07
    kers
    -0.06
    .is
    -0.06
    かって
    -0.06
     "{{
    -0.06
     Carr
    -0.06
     hal
    -0.06
    884
    -0.06
    -0.06
    520
    -0.06
    POSITIVE LOGITS
    /Typography
    0.07
     повер
    0.06
    ließ
    0.06
    voří
    0.06
     hton
    0.06
     arsch
    0.06
     imread
    0.06
     pygame
    0.06
     Puppy
    0.06
     hepatitis
    0.06
    Act Density 0.012%

    No Known Activations