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

    Neuronpedia

    INDEX
    Explanations

    compatibility, support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ripple
    -0.07
    Flag
    -0.07
     subdivision
    -0.06
     loyalty
    -0.06
    extension
    -0.06
    DBG
    -0.06
    总
    -0.06
     Pv
    -0.06
    }s
    -0.06
    Pan
    -0.06
    POSITIVE LOGITS
     окт
    0.07
     مر
    0.07
     examined
    0.07
     weapon
    0.07
     Goal
    0.06
    ""↵
    0.06
     mode
    0.06
    ponsive
    0.06
     xml
    0.06
     conect
    0.06
    Act Density 0.081%

    No Known Activations