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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mower
    -0.08
    oris
    -0.07
    002
    -0.06
     bearings
    -0.06
    494
    -0.06
    ERRY
    -0.06
    isode
    -0.06
    974
    -0.06
    GREEN
    -0.06
     envoy
    -0.06
    POSITIVE LOGITS
     Ihr
    0.07
    /&
    0.07
    包
    0.06
    Clear
    0.06
     Linear
    0.06
     escal
    0.06
    .arguments
    0.06
    Slow
    0.06
     memor
    0.06
    ulong
    0.06
    Act Density 0.014%

    No Known Activations