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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    řik
    -0.07
    ाकर
    -0.06
     個
    -0.06
     проведення
    -0.06
    ุค
    -0.06
     doctoral
    -0.06
    .raise
    -0.06
    atch
    -0.06
    ana
    -0.06
    erialize
    -0.06
    POSITIVE LOGITS
    Addresses
    0.07
     بسي
    0.06
    ']]↵
    0.06
    ivement
    0.06
    ',(
    0.06
    (currency
    0.06
     helm
    0.06
     @"↵
    0.06
     recommends
    0.06
    Sou
    0.06
    Act Density 0.022%

    No Known Activations