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

    Neuronpedia

    INDEX
    Explanations

    Conditional clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '::
    -0.07
     рождения
    -0.06
    Reality
    -0.06
    bullet
    -0.06
    .visual
    -0.06
     مست
    -0.06
     magnet
    -0.06
     lottery
    -0.06
     чуд
    -0.06
    Displayed
    -0.06
    POSITIVE LOGITS
     adaptor
    0.07
    (len
    0.07
     طبقه
    0.06
          ↵      ↵
    0.06
     deset
    0.06
    .Sprintf
    0.06
     愛
    0.06
     ремонт
    0.06
    President
    0.06
     Portable
    0.06
    Act Density 0.000%

    No Known Activations