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

    Neuronpedia

    INDEX
    Explanations

    medical diagnoses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rental
    -0.07
    ollision
    -0.06
     intervals
    -0.06
    ne
    -0.06
     populated
    -0.06
     textile
    -0.06
    =P
    -0.06
     initials
    -0.06
    ьогодні
    -0.06
    lot
    -0.06
    POSITIVE LOGITS
    categorias
    0.08
     Anh
    0.07
     kterých
    0.07
    AutoresizingMask
    0.06
     sleeps
    0.06
     they
    0.06
    Ш
    0.06
     esper
    0.06
    لمان
    0.06
    尿
    0.06
    Act Density 0.015%

    No Known Activations