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

    Neuronpedia

    INDEX
    Explanations

    Box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’
    -0.07
     mh
    -0.06
     κύ
    -0.06
     evolve
    -0.06
    е
    -0.06
     Аль
    -0.06
     embassy
    -0.06
    av
    -0.06
     general
    -0.06
    (do
    -0.06
    POSITIVE LOGITS
    #echo
    0.07
    upuncture
    0.07
    접
    0.06
    _place
    0.06
    Hand
    0.06
     специалист
    0.06
     είχαν
    0.06
    üfus
    0.06
     LOW
    0.06
    ISE
    0.06
    Act Density 0.000%

    No Known Activations