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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    forecast
    -0.07
     weit
    -0.07
    .community
    -0.07
     Cities
    -0.06
     contrace
    -0.06
    -upload
    -0.06
     dissolved
    -0.06
     AssertionError
    -0.06
     Seb
    -0.06
     cyber
    -0.06
    POSITIVE LOGITS
    _low
    0.06
     Wil
    0.06
     In
    0.06
    enth
    0.06
     towards
    0.06
     indie
    0.06
    іна
    0.06
    ING
    0.06
     bust
    0.06
    Dans
    0.06
    Act Density 0.016%

    No Known Activations