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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ipt
    -0.07
    emand
    -0.07
     ^^
    -0.06
     hides
    -0.06
     overnight
    -0.06
    Someone
    -0.06
    Pipe
    -0.06
     ***!↵
    -0.06
     Elli
    -0.06
     Marriott
    -0.06
    POSITIVE LOGITS
    ská
    0.06
     зуп
    0.06
     Михай
    0.06
    지고
    0.06
    icl
    0.06
    _seg
    0.06
     ghi
    0.06
    lius
    0.06
     Timing
    0.06
    _tipo
    0.06
    Act Density 0.003%

    No Known Activations