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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     receptive
    -0.07
     що
    -0.07
    Domain
    -0.06
     през
    -0.06
    Dire
    -0.06
    idity
    -0.06
     چه
    -0.06
    त
    -0.06
    Considering
    -0.06
     retali
    -0.06
    POSITIVE LOGITS
    tab
    0.06
    ORG
    0.06
    RT
    0.06
    -ng
    0.06
    AYER
    0.06
     dumpsters
    0.06
    .execSQL
    0.06
    askan
    0.06
    .Input
    0.05
    weapons
    0.05
    Act Density 0.055%

    No Known Activations