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

    Neuronpedia

    INDEX
    Explanations

    Prisms and geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jenje
    -0.10
     અનુસાર
    -0.09
     જાહેર
    -0.07
     సంప
    -0.07
     traditional
    -0.07
     Jr
    -0.07
     App
    -0.07
     Mega
    -0.07
     Romano
    -0.07
     норм
    -0.07
    POSITIVE LOGITS
     vols
    0.09
     �
    0.09
     слой
    0.09
     этаж
    0.09
     �
    0.08
    islation
    0.08
     stere
    0.08
     눈
    0.08
    층
    0.08
    尸
    0.08
    Act Density 0.015%

    No Known Activations