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

    Neuronpedia

    INDEX
    Explanations

    write

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    House
    -0.07
     cũng
    -0.07
    ΩΤ
    -0.06
     Peterson
    -0.06
     september
    -0.06
     faaliyet
    -0.06
    TRIES
    -0.06
    Scalars
    -0.06
    Tooltip
    -0.06
     reducer
    -0.06
    POSITIVE LOGITS
    /write
    0.07
    Write
    0.06
    он
    0.06
    .win
    0.06
    di
    0.06
     ремонт
    0.06
    terior
    0.06
    ,—
    0.05
    剧
    0.05
     automation
    0.05
    Act Density 0.016%

    No Known Activations