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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atta
    -0.07
     route
    -0.07
    utto
    -0.07
    ensions
    -0.07
    ソン
    -0.06
    _route
    -0.06
    Eine
    -0.06
    :list
    -0.06
    awning
    -0.06
    وني
    -0.06
    POSITIVE LOGITS
     inval
    0.06
     závě
    0.06
     coi
    0.06
     offices
    0.06
     Volt
    0.06
     пок
    0.06
    .ToDateTime
    0.06
     banners
    0.06
     apprentice
    0.06
     setInput
    0.06
    Act Density 0.004%

    No Known Activations