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
    externalActionCode
    -0.07
     scrut
    -0.07
    дрес
    -0.07
    Revision
    -0.06
    crest
    -0.06
    }))↵
    -0.06
    .Keyboard
    -0.06
    ,､
    -0.06
     kỷ
    -0.06
    τικών
    -0.06
    POSITIVE LOGITS
     contestant
    0.07
     gelen
    0.07
     contributes
    0.07
     accomplished
    0.06
     soaked
    0.06
    ститу
    0.06
     Obamacare
    0.06
    AMPLE
    0.06
    -American
    0.06
    (device
    0.06
    Act Density 0.034%

    No Known Activations