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

    Neuronpedia

    INDEX
    Explanations

    Composing or requesting emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     herein
    -0.08
    ehicles
    -0.08
    eders
    -0.08
    üsü
    -0.08
    et
    -0.08
     thereto
    -0.07
     realized
    -0.07
    _PHASE
    -0.07
    iënt
    -0.07
     ebb
    -0.07
    POSITIVE LOGITS
     cowork
    0.09
     colleague
    0.09
     classmates
    0.09
    远
    0.08
     भेज
    0.08
     remoto
    0.08
    某
    0.08
     napis
    0.08
     Dropbox
    0.08
     محتر
    0.08
    Act Density 0.023%

    No Known Activations