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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [item
    -0.07
     сіль
    -0.06
    ToList
    -0.06
    uvre
    -0.06
    fort
    -0.06
    스크
    -0.06
     lực
    -0.06
     bn
    -0.06
     cabeza
    -0.06
    也
    -0.06
    POSITIVE LOGITS
     ringing
    0.08
    PushButton
    0.07
    .reflect
    0.07
    eny
    0.07
     SHA
    0.07
     Networking
    0.07
    efined
    0.06
     then
    0.06
     anne
    0.06
     unter
    0.06
    Act Density 0.026%

    No Known Activations