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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worksheets
    -0.07
    partition
    -0.07
     concentrating
    -0.07
    Template
    -0.07
     करन
    -0.06
     Svens
    -0.06
     Пов
    -0.06
     workflow
    -0.06
     antagon
    -0.06
     grains
    -0.06
    POSITIVE LOGITS
    اءات
    0.06
     NotificationCenter
    0.06
    نا
    0.06
    (UnmanagedType
    0.06
     argues
    0.06
     İlk
    0.06
     uvol
    0.06
    ）、
    0.06
    空
    0.06
    ází
    0.06
    Act Density 0.006%

    No Known Activations