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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .requestFocus
    -0.07
     Cush
    -0.06
    eceğiz
    -0.06
     уровне
    -0.06
     공격
    -0.06
     impairment
    -0.06
     Months
    -0.06
    lední
    -0.06
     оці
    -0.06
    „ظ
    -0.06
    POSITIVE LOGITS
    vic
    0.07
     resize
    0.06
     declining
    0.06
     noi
    0.06
     uneven
    0.06
     TOK
    0.06
     invis
    0.06
     paraph
    0.06
    Flag
    0.06
     runtime
    0.06
    Act Density 0.008%

    No Known Activations