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

    Neuronpedia

    INDEX
    Explanations

    analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stag
    -0.07
    CONDITION
    -0.06
    ’T
    -0.06
     disks
    -0.06
     MART
    -0.06
    alyze
    -0.06
     Margaret
    -0.06
     SVM
    -0.06
     await
    -0.06
    !=
    -0.06
    POSITIVE LOGITS
    (regex
    0.07
     paralle
    0.07
     Ancient
    0.06
     Poster
    0.06
    ILog
    0.06
    �
    0.06
     fencing
    0.06
     scour
    0.06
    aporation
    0.06
    443
    0.06
    Act Density 0.024%

    No Known Activations