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

    Neuronpedia

    INDEX
    Explanations

    When

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     msgs
    -0.07
     Orr
    -0.07
    альная
    -0.06
    uffix
    -0.06
     cups
    -0.06
     resumes
    -0.06
    ??
    -0.06
     altitude
    -0.06
     ekonomik
    -0.06
     olduk
    -0.06
    POSITIVE LOGITS
    KHR
    0.06
    Portály
    0.06
     wer
    0.06
    atherine
    0.06
     fireEvent
    0.06
     kidney
    0.06
    ruary
    0.06
     harms
    0.06
    (ignore
    0.06
    ,left
    0.06
    Act Density 0.017%

    No Known Activations