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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oyun
    -0.07
     ذات
    -0.06
     vàng
    -0.06
     Dos
    -0.06
    /storage
    -0.06
     závě
    -0.06
     Reef
    -0.06
    -finals
    -0.06
     Roosevelt
    -0.06
     penet
    -0.06
    POSITIVE LOGITS
     раді
    0.07
    ляються
    0.07
     shoes
    0.07
    ісля
    0.06
    ॉप
    0.06
    -mails
    0.06
    効
    0.06
    είται
    0.06
    国产
    0.06
    pter
    0.06
    Act Density 0.036%

    No Known Activations