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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detecting
    -0.06
     procur
    -0.06
    'use
    -0.06
    ological
    -0.06
    .oc
    -0.06
     taking
    -0.06
    =new
    -0.06
     utens
    -0.06
    従
    -0.06
    =root
    -0.06
    POSITIVE LOGITS
    .</
    0.06
    右
    0.06
    等
    0.06
    trash
    0.06
     least
    0.06
    uptime
    0.06
    BundleOrNil
    0.06
    toJson
    0.06
    ANCEL
    0.06
    HEADER
    0.06
    Act Density 0.031%

    No Known Activations