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

    Neuronpedia

    INDEX
    Explanations

    Directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _history
    -0.06
     Raises
    -0.06
     Taste
    -0.06
     taste
    -0.06
    starter
    -0.06
    Dans
    -0.06
     جزء
    -0.06
     flows
    -0.06
    artic
    -0.06
     decimals
    -0.06
    POSITIVE LOGITS
     všichni
    0.08
     wz
    0.07
     Wrap
    0.07
     =↵
    0.06
     scramble
    0.06
    ../../../
    0.06
     약
    0.06
    mut
    0.06
     νό
    0.06
     پیشنه
    0.06
    Act Density 0.009%

    No Known Activations