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

    Neuronpedia

    INDEX
    Explanations

    tr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dictator
    -0.07
     Classes
    -0.06
     Harold
    -0.06
     policeman
    -0.06
     analsex
    -0.06
     квад
    -0.06
    Nice
    -0.06
    566
    -0.06
     Century
    -0.06
     reinforced
    -0.06
    POSITIVE LOGITS
    mmo
    0.07
    であり
    0.06
    min
    0.06
     dikkate
    0.06
    Operating
    0.06
     stare
    0.06
    wh
    0.06
     deline
    0.06
    ("""
    0.06
    κει
    0.06
    Act Density 0.018%

    No Known Activations