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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uese
    -0.07
     глаз
    -0.07
    10
    -0.07
    ایان
    -0.06
     کشور
    -0.06
    ість
    -0.06
     Independent
    -0.06
     INIT
    -0.06
     chair
    -0.06
    ASURE
    -0.06
    POSITIVE LOGITS
     affect
    0.06
    preferred
    0.06
    TW
    0.06
     pequ
    0.06
    insi
    0.06
    .rev
    0.06
    ога
    0.06
    iselect
    0.06
    эн
    0.06
     fc
    0.06
    Act Density 0.022%

    No Known Activations