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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Swamp
    -0.07
     Republican
    -0.06
     piston
    -0.06
    _No
    -0.06
     GANG
    -0.06
    _container
    -0.06
     руч
    -0.06
     Freund
    -0.06
    _MISSING
    -0.06
     fist
    -0.06
    POSITIVE LOGITS
     о
    0.07
    イト
    0.07
    ımızda
    0.07
    cter
    0.07
    [date
    0.07
    relations
    0.07
     sắc
    0.07
     wors
    0.07
     flashlight
    0.06
    DevExpress
    0.06
    Act Density 0.005%

    No Known Activations