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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     francais
    -0.07
     класс
    -0.07
    <center
    -0.07
    Cart
    -0.07
     opsiyon
    -0.06
     nodo
    -0.06
     mortar
    -0.06
    ast
    -0.06
     форме
    -0.06
     maliyet
    -0.06
    POSITIVE LOGITS
     valued
    0.08
    eline
    0.07
     TIM
    0.07
     highly
    0.07
     esteemed
    0.07
    гля
    0.06
     hãng
    0.06
     Stephen
    0.06
     prized
    0.06
    unate
    0.06
    Act Density 0.010%

    No Known Activations