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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΙΣΤ
    -0.07
    470
    -0.07
    -0.07
     fmt
    -0.06
    kenin
    -0.06
     เก
    -0.06
    ้
    -0.06
     intertwined
    -0.06
     Vương
    -0.06
     melee
    -0.06
    POSITIVE LOGITS
     setMessage
    0.07
     Telerik
    0.06
    .Expression
    0.06
    اکم
    0.06
     underscores
    0.06
     wars
    0.06
    _subtitle
    0.06
    perse
    0.05
    طم
    0.05
     orderId
    0.05
    Act Density 0.017%

    No Known Activations