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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人才
    -0.07
     dříve
    -0.07
    感到
    -0.07
    ladı
    -0.07
     estaba
    -0.07
     friction
    -0.06
    ۲۴
    -0.06
    Nothing
    -0.06
    Ticker
    -0.06
    poň
    -0.06
    POSITIVE LOGITS
    etSocketAddress
    0.07
    _AES
    0.07
    AlgorithmException
    0.06
     ตำ
    0.06
    fl
    0.06
    愿
    0.06
    ":""
    0.06
     impl
    0.06
    spe
    0.06
    BYTES
    0.06
    Act Density 0.026%

    No Known Activations