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
     trú
    -0.06
     Kant
    -0.06
     왔
    -0.06
    το
    -0.06
    cdb
    -0.06
     menace
    -0.05
    performance
    -0.05
     دم
    -0.05
    adratic
    -0.05
     defaults
    -0.05
    POSITIVE LOGITS
     debts
    0.08
    egin
    0.07
     TOTAL
    0.07
    ouce
    0.07
    illed
    0.07
    latable
    0.06
    جوی
    0.06
    (down
    0.06
    emean
    0.06
    <User
    0.06
    Act Density 0.109%

    No Known Activations