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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ียนร
    -0.06
     корот
    -0.06
     nós
    -0.06
     Bris
    -0.06
     vyjád
    -0.06
    yyy
    -0.06
    :::::::::
    -0.06
     свою
    -0.06
    operators
    -0.06
     Karel
    -0.06
    POSITIVE LOGITS
    	raw
    0.07
     logos
    0.07
     lady
    0.07
     deport
    0.07
    clin
    0.06
    ieme
    0.06
    _patch
    0.06
     dns
    0.06
    _find
    0.06
    тот
    0.06
    Act Density 0.042%

    No Known Activations