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

    Neuronpedia

    INDEX
    Explanations

    lock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sund
    -0.07
     недел
    -0.07
    行く
    -0.06
     foul
    -0.06
    헵
    -0.06
    Nor
    -0.06
    cry
    -0.06
     Deal
    -0.06
     umbrella
    -0.06
     Crash
    -0.06
    POSITIVE LOGITS
    'ai
    0.07
    ==========
    0.07
    oldemort
    0.07
     gọn
    0.07
    ********
    0.07
    cidade
    0.07
    mob
    0.07
    Prototype
    0.07
     bst
    0.07
    ==============
    0.06
    Act Density 0.019%

    No Known Activations