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

    Neuronpedia

    INDEX
    Explanations

    ziplock bags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    節
    -0.08
     overwritten
    -0.07
     iliş
    -0.07
    ноп
    -0.06
     superf
    -0.06
     تب
    -0.06
    ुग
    -0.06
     artillery
    -0.06
    igon
    -0.06
     Рег
    -0.06
    POSITIVE LOGITS
     Blade
    0.07
     paj
    0.06
     fold
    0.06
    .forEach
    0.06
     DIG
    0.06
    ))"↵
    0.06
     funcs
    0.06
     NSLog
    0.06
     Matte
    0.06
     env
    0.06
    Act Density 0.012%

    No Known Activations