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

    Neuronpedia

    INDEX
    Explanations

    center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izing
    -0.07
    rip
    -0.07
     Pension
    -0.07
    lected
    -0.07
     Song
    -0.07
    λ
    -0.06
    제
    -0.06
     Hond
    -0.06
     prizes
    -0.06
    解
    -0.06
    POSITIVE LOGITS
    EntityManager
    0.07
    ║
    0.07
     لدينا
    0.07
     منطقة
    0.07
    ALTER
    0.07
     criar
    0.07
    ////////////////////////////////////////////////////////////////
    0.07
    'à
    0.07
    _AM
    0.07
    	AT
    0.06
    Act Density 0.030%

    No Known Activations