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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DLL
    -0.07
    蒙
    -0.07
     ndarray
    -0.07
    _Print
    -0.07
    물
    -0.06
    004
    -0.06
    categoryId
    -0.06
    츠
    -0.06
    лади
    -0.06
    -insert
    -0.06
    POSITIVE LOGITS
    croft
    0.06
    oto
    0.06
     cost
    0.06
    lessly
    0.06
     başlam
    0.06
    erator
    0.06
     scam
    0.06
    .vote
    0.06
    owards
    0.06
     timing
    0.06
    Act Density 0.021%

    No Known Activations