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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UGIN
    -0.08
     Після
    -0.07
     livre
    -0.07
     byste
    -0.06
     Lie
    -0.06
    _Surface
    -0.06
     الکتر
    -0.06
    uffers
    -0.06
    çon
    -0.06
     glacier
    -0.06
    POSITIVE LOGITS
    .sh
    0.07
     parked
    0.06
    ())->
    0.06
    ，他们
    0.06
    	Map
    0.06
    مم
    0.06
    ц
    0.06
    *i
    0.06
    コ
    0.06
    ne
    0.06
    Act Density 0.000%

    No Known Activations