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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cessation
    -0.06
    高度
    -0.06
    )a
    -0.06
    ですね
    -0.06
    iten
    -0.06
    ede
    -0.06
    Okay
    -0.06
     mse
    -0.06
     Thatcher
    -0.06
    λλην
    -0.06
    POSITIVE LOGITS
     Oracle
    0.07
     Anthony
    0.07
    Enumer
    0.07
    ovaný
    0.07
     task
    0.06
     gather
    0.06
     movers
    0.06
     uzav
    0.06
     reacting
    0.06
    (selected
    0.06
    Act Density 0.006%

    No Known Activations