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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     denně
    -0.07
    'It
    -0.06
    male
    -0.06
     pastor
    -0.06
     сразу
    -0.06
    vo
    -0.06
     ########
    -0.06
     '@
    -0.06
    рий
    -0.06
    ешь
    -0.06
    POSITIVE LOGITS
     قانون
    0.07
    �
    0.07
    [K
    0.06
     Pla
    0.06
     Merch
    0.06
    iParam
    0.06
     ******************************************************************************/↵↵
    0.06
     ([[
    0.06
    Finite
    0.06
    .Focused
    0.06
    Act Density 0.076%

    No Known Activations