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

    Neuronpedia

    INDEX
    Explanations

    give

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fleet
    -0.07
    busy
    -0.06
     paused
    -0.06
     Imaging
    -0.06
    cobra
    -0.06
     декоратив
    -0.06
     άλλ
    -0.06
     Mund
    -0.06
     Mesh
    -0.06
     outfile
    -0.06
    POSITIVE LOGITS
    Platform
    0.07
     Ally
    0.07
    //*[@
    0.06
     nec
    0.06
     월세
    0.06
    Signing
    0.06
     kal
    0.06
     Sharia
    0.06
    Allowed
    0.06
    (&:
    0.06
    Act Density 0.010%

    No Known Activations