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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     siege
    -0.07
    ुज
    -0.07
    悟
    -0.07
    šel
    -0.07
     Super
    -0.06
    �
    -0.06
     GOP
    -0.06
     offend
    -0.06
     reality
    -0.06
     Inv
    -0.06
    POSITIVE LOGITS
     Dissertation
    0.07
     pís
    0.06
    azu
    0.06
     forearm
    0.06
    elps
    0.06
    _Des
    0.06
    est
    0.06
    を作
    0.06
     eject
    0.06
     THESE
    0.06
    Act Density 0.066%

    No Known Activations