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

    Neuronpedia

    INDEX
    Explanations

    short

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Capitol
    -0.07
    lessly
    -0.06
    태
    -0.06
    inverse
    -0.06
    .testng
    -0.06
    .Zero
    -0.06
     thereof
    -0.06
     displacement
    -0.06
    plugins
    -0.06
     arc
    -0.06
    POSITIVE LOGITS
    [new
    0.07
     woke
    0.07
     yans
    0.06
    期间
    0.06
     Sims
    0.06
     biển
    0.06
    HCI
    0.06
     grew
    0.06
     rgb
    0.06
     και
    0.06
    Act Density 0.057%

    No Known Activations