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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่ง
    -0.07
     hayata
    -0.07
     mnoha
    -0.07
    하고
    -0.07
     werde
    -0.07
    +"&
    -0.07
    //@
    -0.07
    われた
    -0.06
    andidates
    -0.06
     oleh
    -0.06
    POSITIVE LOGITS
     Reader
    0.06
    FileNotFoundException
    0.06
    い
    0.06
    uous
    0.06
    bble
    0.06
     flushing
    0.06
    ♀♀♀♀
    0.06
     whipped
    0.06
    anne
    0.06
     GRAPH
    0.06
    Act Density 0.001%

    No Known Activations