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

    Neuronpedia

    INDEX
    Explanations

    Marketing/advertising content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pass
    -0.07
    등
    -0.07
     longitude
    -0.06
     等
    -0.06
    .ship
    -0.06
     пог
    -0.06
    (pass
    -0.06
    垂
    -0.06
     pet
    -0.06
    ugu
    -0.06
    POSITIVE LOGITS
    ":[{↵
    0.06
     фунда
    0.06
    ても
    0.06
    azing
    0.06
     атмос
    0.06
     Reference
    0.06
     bozuk
    0.06
     gentlemen
    0.06
     Türkiye
    0.06
    ibia
    0.06
    Act Density 0.235%

    No Known Activations