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

    Neuronpedia

    INDEX
    Explanations

    Escalators and rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ambara
    -0.09
     нож
    -0.09
     Redistributions
    -0.09
     мышцы
    -0.09
     просмотр
    -0.08
     deserves
    -0.08
     обладает
    -0.08
     обладают
    -0.08
     agrad
    -0.08
    fiets
    -0.08
    POSITIVE LOGITS
     number
    0.08
     Sociedad
    0.07
    eban
    0.07
     here
    0.07
    _NUMBER
    0.07
     Bard
    0.07
    Number
    0.07
     tp
    0.07
     cit
    0.07
    ypad
    0.07
    Act Density 0.001%

    No Known Activations