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

    Neuronpedia

    INDEX
    Explanations

    cooking instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _processors
    -0.09
     verwerken
    -0.08
     प्रक्रिया
    -0.08
     the
    -0.07
     verwerkt
    -0.07
     criminal
    -0.07
     Processing
    -0.07
     Rel
    -0.07
     processed
    -0.07
     accept
    -0.07
    POSITIVE LOGITS
     крыш
    0.12
    omeje
    0.09
     techo
    0.09
    盖
    0.09
    พัก
    0.09
    oglobin
    0.09
     خواب
    0.09
    :hidden
    0.08
     shielding
    0.08
    acious
    0.08
    Act Density 0.009%

    No Known Activations