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

    Neuronpedia

    INDEX
    Explanations

    image

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kadar
    -0.06
     cylinder
    -0.06
    /.
    -0.06
     tand
    -0.06
     rear
    -0.06
     verst
    -0.06
     soaring
    -0.06
     exe
    -0.06
     tham
    -0.06
    haf
    -0.06
    POSITIVE LOGITS
    (predictions
    0.07
     Больш
    0.07
     Cut
    0.07
    laughter
    0.07
    xbd
    0.06
    αρα
    0.06
     زیاد
    0.06
    PCS
    0.06
    %"><
    0.06
    атора
    0.06
    Act Density 0.001%

    No Known Activations