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

    Neuronpedia

    INDEX
    Explanations

    code comments/source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lup
    -0.06
     Opportunities
    -0.06
    Bullet
    -0.06
     инвести
    -0.06
    errupt
    -0.06
     Enables
    -0.06
     slice
    -0.06
    Enemy
    -0.06
    нг
    -0.06
     highest
    -0.06
    POSITIVE LOGITS
    arih
    0.08
    (REG
    0.07
    .prefix
    0.07
     респ
    0.07
    ώς
    0.06
     แก
    0.06
     أيض
    0.06
     sich
    0.06
    _Header
    0.06
     veriyor
    0.06
    Act Density 0.006%

    No Known Activations