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

    Neuronpedia

    INDEX
    Explanations

    ..

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mustard
    -0.07
     lur
    -0.07
    #================================================================
    -0.06
     bruises
    -0.06
    leg
    -0.06
    inces
    -0.06
    における
    -0.06
     arrog
    -0.06
     ALOG
    -0.06
     клі
    -0.06
    POSITIVE LOGITS
    ('{}
    0.07
     hydrated
    0.06
    *=
    0.06
     prise
    0.06
    활동
    0.06
     efficiencies
    0.05
     dél
    0.05
    —an
    0.05
    (root
    0.05
     režim
    0.05
    Act Density 0.002%

    No Known Activations