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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /my
    -0.07
     Compile
    -0.06
    ocrisy
    -0.06
     thinker
    -0.06
     Publisher
    -0.06
     seinem
    -0.06
     His
    -0.06
     absolutely
    -0.06
    ł
    -0.06
     les
    -0.06
    POSITIVE LOGITS
     initialize
    0.07
    -pres
    0.07
     Visual
    0.07
     punched
    0.06
    ,total
    0.06
     спортив
    0.06
    unday
    0.06
    -touch
    0.06
     тай
    0.06
     предпол
    0.06
    Act Density 0.015%

    No Known Activations