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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lng
    -0.07
    _OFF
    -0.07
    С
    -0.07
     Concurrent
    -0.06
     bear
    -0.06
     distrust
    -0.06
    -paper
    -0.06
    “They
    -0.06
    combined
    -0.06
     BOT
    -0.06
    POSITIVE LOGITS
    ілля
    0.07
     Україні
    0.06
     sorun
    0.06
     부탁
    0.06
     domu
    0.06
     Computing
    0.06
     bueno
    0.06
    guid
    0.06
     automáticamente
    0.06
     DataSource
    0.06
    Act Density 0.001%

    No Known Activations