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

    Neuronpedia

    INDEX
    Explanations

    Measuring by weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finalidade
    -0.08
     publicly
    -0.08
    ্ধ
    -0.08
     делать
    -0.08
     tout
    -0.08
     preoc
    -0.07
     предлож
    -0.07
    ूं
    -0.07
    CLUDED
    -0.07
    Biography
    -0.07
    POSITIVE LOGITS
     Stre
    0.08
     dich
    0.07
    adc
    0.07
     keyboards
    0.07
     Mack
    0.07
    (pack
    0.07
     pequenos
    0.07
    ysm
    0.07
    _PIX
    0.07
     সবচ
    0.07
    Act Density 0.008%

    No Known Activations