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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    福利
    -0.08
    уст
    -0.07
     önce
    -0.07
    (dataSource
    -0.07
     weit
    -0.07
    الث
    -0.07
    functions
    -0.07
     honorable
    -0.07
    πον
    -0.07
     soutěže
    -0.06
    POSITIVE LOGITS
     DELETE
    0.06
     transgender
    0.06
     Hitler
    0.06
    )][
    0.06
    )return
    0.06
    _SUS
    0.06
    .fig
    0.06
    305
    0.06
    ()"↵
    0.05
     danced
    0.05
    Act Density 0.016%

    No Known Activations