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

    Neuronpedia

    INDEX
    Explanations

    :image

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    枘
    -0.07
    ropol
    -0.07
     culpa
    -0.07
    igenous
    -0.07
    新たな
    -0.07
    incible
    -0.06
    深入了解
    -0.06
     şü
    -0.06
     factura
    -0.06
    编写
    -0.06
    POSITIVE LOGITS
     Aer
    0.07
    _application
    0.07
    飛
    0.07
     WD
    0.07
     buoy
    0.06
    _cred
    0.06
    (vector
    0.06
    Sys
    0.06
    digits
    0.06
     Об
    0.06
    Act Density 0.001%

    No Known Activations