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

    Neuronpedia

    INDEX
    Explanations

    ariat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     koy
    -0.07
     Cluster
    -0.06
     present
    -0.06
     Procedures
    -0.06
    _increase
    -0.06
    _activity
    -0.06
    >|
    -0.06
    oader
    -0.06
    ]
    -0.05
    ьи
    -0.05
    POSITIVE LOGITS
    rese
    0.07
    .Reset
    0.07
     resets
    0.07
     BufferedWriter
    0.06
    lesc
    0.06
    /client
    0.06
    918
    0.06
     renters
    0.06
     lil
    0.06
     يش
    0.06
    Act Density 0.005%

    No Known Activations