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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Export
    -0.07
    待
    -0.07
     ﾞ
    -0.06
    gpu
    -0.06
     beating
    -0.06
    #================================================================
    -0.06
     cheating
    -0.06
    imp
    -0.06
    )”
    -0.06
     Worker
    -0.06
    POSITIVE LOGITS
     Supplements
    0.07
    enment
    0.06
    ствен
    0.06
    Ц
    0.06
     DNS
    0.06
     ePub
    0.06
    xampp
    0.06
     nějak
    0.06
    ازه
    0.05
    xmax
    0.05
    Act Density 0.022%

    No Known Activations