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

    Neuronpedia

    INDEX
    Explanations

    Pro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .kode
    -0.07
     pund
    -0.07
    secondary
    -0.07
    analyze
    -0.07
     chan
    -0.06
    793
    -0.06
    nos
    -0.06
    ety
    -0.06
    .null
    -0.06
    seudo
    -0.06
    POSITIVE LOGITS
    .ylabel
    0.06
    H
    0.06
    ĩa
    0.06
    (dy
    0.06
     dejting
    0.06
     دع
    0.06
     recycled
    0.05
     spotting
    0.05
    asp
    0.05
    	EXPECT
    0.05
    Act Density 0.004%

    No Known Activations