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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Daily
    -0.07
     atd
    -0.07
    .students
    -0.07
     Avery
    -0.06
    ذار
    -0.06
    koneksi
    -0.06
     Arbor
    -0.06
    ictionary
    -0.06
    Daily
    -0.06
     wię
    -0.06
    POSITIVE LOGITS
    ูปแบบ
    0.06
    ucing
    0.06
     fleece
    0.06
    otte
    0.06
    	gl
    0.06
    的是
    0.06
     unleash
    0.05
     spine
    0.05
    "/>↵
    0.05
     Wag
    0.05
    Act Density 0.012%

    No Known Activations