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

    Neuronpedia

    INDEX
    Explanations

    element

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estudio
    -0.07
    modity
    -0.07
    Connection
    -0.07
     soph
    -0.06
     Automation
    -0.06
    ść
    -0.06
     Ao
    -0.06
     blockbuster
    -0.06
     repayment
    -0.06
    등
    -0.06
    POSITIVE LOGITS
    vi
    0.07
    б
    0.06
    ilters
    0.06
    orderId
    0.06
    /renderer
    0.06
    #from
    0.06
    لیم
    0.06
     Rosenberg
    0.06
    enguin
    0.06
    -alt
    0.06
    Act Density 0.000%

    No Known Activations