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

    Neuronpedia

    INDEX
    Explanations

    ax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wheels
    -0.07
     :]↵
    -0.07
    +'/'+
    -0.07
     nn
    -0.07
     Trick
    -0.07
    _Back
    -0.06
     Space
    -0.06
     Billy
    -0.06
    Leap
    -0.06
     resist
    -0.06
    POSITIVE LOGITS
     tok
    0.07
    交易
    0.07
    екту
    0.06
    reported
    0.06
    IntegerField
    0.06
    (cancel
    0.06
     incentiv
    0.06
     तस
    0.06
    zp
    0.06
    容
    0.06
    Act Density 0.002%

    No Known Activations