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

    Neuronpedia

    INDEX
    Explanations

    inventions and technical fixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (reinterpret
    -0.07
    .(
    -0.07
     安
    -0.07
     Crop
    -0.07
     Jurassic
    -0.07
     افراد
    -0.06
     Dataset
    -0.06
    /apis
    -0.06
    _geo
    -0.06
     ipAddress
    -0.06
    POSITIVE LOGITS
     بيت
    0.06
    IMIZE
    0.06
     Hit
    0.06
     strengthen
    0.06
     abide
    0.06
     Deadpool
    0.06
    Hit
    0.06
    _ub
    0.06
     checking
    0.06
    uego
    0.06
    Act Density 0.186%

    No Known Activations