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

    Neuronpedia

    INDEX
    Explanations

    Mechanical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rowse
    -0.07
     screams
    -0.07
     arteries
    -0.07
    VK
    -0.07
    >n
    -0.07
    auge
    -0.07
     Dixon
    -0.06
     kilometres
    -0.06
     multinational
    -0.06
    ạnh
    -0.06
    POSITIVE LOGITS
    ivr
    0.06
    (Column
    0.06
     burned
    0.06
     řekl
    0.06
     الأف
    0.06
     fellow
    0.06
    。\
    0.06
     lul
    0.06
    .comm
    0.06
    [:]
    0.06
    Act Density 0.034%

    No Known Activations