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

    Neuronpedia

    INDEX
    Explanations

    Specifications or limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kid
    -0.07
    WK
    -0.06
    _tensor
    -0.06
     tension
    -0.06
     liberation
    -0.06
    alnum
    -0.06
     bounding
    -0.06
    .WebServlet
    -0.06
     الوقت
    -0.06
     Spaces
    -0.06
    POSITIVE LOGITS
     corn
    0.07
     Paris
    0.07
     qt
    0.06
     reasoned
    0.06
    .ImageTransparentColor
    0.06
     appointments
    0.06
     жод
    0.06
    ,next
    0.06
    card
    0.06
     muž
    0.06
    Act Density 0.253%

    No Known Activations