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

    Neuronpedia

    INDEX
    Explanations

    pool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    work
    -0.07
    责任
    -0.07
     sustain
    -0.06
    erve
    -0.06
    賢
    -0.06
    IZED
    -0.06
    /core
    -0.06
     какой
    -0.06
     فرد
    -0.06
     activate
    -0.06
    POSITIVE LOGITS
    .Array
    0.07
     CheckBox
    0.07
     actress
    0.07
    Ot
    0.06
     ought
    0.06
     Attribution
    0.06
    ịa
    0.06
    %@
    0.06
    olleyError
    0.06
     кер
    0.06
    Act Density 0.002%

    No Known Activations