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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    альне
    -0.07
     ↵	↵
    -0.07
     IonicModule
    -0.06
    King
    -0.06
     طی
    -0.06
    uien
    -0.06
     Lake
    -0.06
    _pk
    -0.06
    ↵            
↵
    -0.06
     区
    -0.06
    POSITIVE LOGITS
     numbers
    0.13
     Numbers
    0.10
    Numbers
    0.09
    スポ
    0.08
    numbers
    0.07
     Abbas
    0.07
    ummings
    0.06
     overs
    0.06
    sq
    0.06
     amounts
    0.06
    Act Density 0.014%

    No Known Activations