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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DOUBLE
    -0.06
    지원
    -0.06
     Conspiracy
    -0.06
     altre
    -0.06
    ощи
    -0.06
    рах
    -0.06
    оюз
    -0.06
    КА
    -0.06
     는
    -0.06
     poison
    -0.06
    POSITIVE LOGITS
    _com
    0.07
     ratified
    0.07
     sống
    0.07
     recomend
    0.06
    operand
    0.06
     osp
    0.06
    *m
    0.06
     homemade
    0.06
    masının
    0.06
     stake
    0.06
    Act Density 0.126%

    No Known Activations