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

    Neuronpedia

    INDEX
    Explanations

    ider

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inya
    -0.07
    _MAT
    -0.06
    чного
    -0.06
    गढ
    -0.06
     повинен
    -0.06
     ремон
    -0.06
    .loc
    -0.06
    _book
    -0.06
     ли
    -0.06
     argparse
    -0.06
    POSITIVE LOGITS
    ider
    0.08
     submerged
    0.07
     ode
    0.07
     adorable
    0.07
    OSP
    0.07
     chlor
    0.07
     edible
    0.07
    Sch
    0.06
    ọn
    0.06
    eterangan
    0.06
    Act Density 0.001%

    No Known Activations