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

    Neuronpedia

    INDEX
    Explanations

    syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    beer
    -0.07
    storage
    -0.06
    unda
    -0.06
    (cid
    -0.06
    DTD
    -0.06
     incremental
    -0.06
     bề
    -0.06
    емати
    -0.06
     cannabin
    -0.06
     cnn
    -0.06
    POSITIVE LOGITS
    言わ
    0.06
     diese
    0.06
     indefinitely
    0.06
    _Object
    0.06
     reconnaissance
    0.06
     inadvertently
    0.06
    usions
    0.06
    。“
    0.06
    之
    0.06
     وضعیت
    0.06
    Act Density 0.166%

    No Known Activations