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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oxel
    -0.07
     jump
    -0.07
     sine
    -0.07
     Geek
    -0.07
     Talk
    -0.07
     платеж
    -0.07
    ¯¯
    -0.07
    dzi
    -0.06
     StatusCode
    -0.06
     gele
    -0.06
    POSITIVE LOGITS
     choosing
    0.10
     selecting
    0.10
     selection
    0.09
     selected
    0.09
     Selection
    0.09
     select
    0.09
     choose
    0.08
    選択
    0.08
    Select
    0.08
     Select
    0.08
    Act Density 0.082%

    No Known Activations