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

    Neuronpedia

    INDEX
    Explanations

    misrepresented

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colony
    -0.07
     фрон
    -0.07
    _footer
    -0.06
    um
    -0.06
    Hello
    -0.06
     Floor
    -0.06
     Languages
    -0.06
     KE
    -0.06
     emperor
    -0.06
     <?
    -0.05
    POSITIVE LOGITS
    OGLE
    0.07
    .accept
    0.07
     ensure
    0.07
    ulates
    0.07
     assures
    0.07
     tiện
    0.06
    Warnings
    0.06
     bilinen
    0.06
    jpeg
    0.06
     elbows
    0.06
    Act Density 0.001%

    No Known Activations