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

    Neuronpedia

    INDEX
    Explanations

    prim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iminal
    -0.07
    ائي
    -0.06
    兴
    -0.06
    اءات
    -0.06
    िच
    -0.06
     ULONG
    -0.06
    号
    -0.06
     شهید
    -0.06
     состояния
    -0.06
     берез
    -0.06
    POSITIVE LOGITS
    .gridx
    0.06
    <select
    0.06
     Hers
    0.06
       ↵
    0.06
    ircon
    0.06
     unaware
    0.06
     tanı
    0.06
     kry
    0.06
     vzdu
    0.06
     derives
    0.06
    Act Density 0.047%

    No Known Activations