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

    Neuronpedia

    INDEX
    Explanations

    again

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vendors
    -0.07
     outperform
    -0.07
     Oy
    -0.07
     freezes
    -0.07
    Ware
    -0.07
     తో
    -0.07
     numerous
    -0.07
     sprinkled
    -0.07
     hood
    -0.07
     extras
    -0.07
    POSITIVE LOGITS
     внимательно
    0.10
     wording
    0.09
     Revised
    0.09
     revise
    0.09
    Reviewed
    0.08
     lại
    0.08
    _members
    0.08
    仔
    0.08
     miembros
    0.08
    看看
    0.08
    Act Density 0.011%

    No Known Activations