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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anse
    -0.08
     Tyson
    -0.07
    -print
    -0.07
     temptation
    -0.07
    eking
    -0.07
     также
    -0.06
    INTR
    -0.06
    ิ้
    -0.06
     -
    -0.06
     traj
    -0.06
    POSITIVE LOGITS
     ($('#
    0.07
     DDR
    0.06
    (mContext
    0.06
    .WebControls
    0.06
    (ok
    0.06
     specialize
    0.06
    SETTINGS
    0.05
    Sau
    0.05
    네요
    0.05
    λικά
    0.05
    Act Density 0.211%

    No Known Activations