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

    Neuronpedia

    INDEX
    Explanations

    Business principles and qualities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )['
    -0.07
    　ﾞ
    -0.07
     буде
    -0.07
    اوية
    -0.06
    脸
    -0.06
    igth
    -0.06
    _barang
    -0.06
    ENGINE
    -0.06
    _PI
    -0.06
     розгля
    -0.06
    POSITIVE LOGITS
     intrig
    0.06
     Alerts
    0.06
    ewan
    0.06
     Laundry
    0.06
    stuff
    0.06
     optional
    0.06
    liches
    0.06
     acoustic
    0.06
     début
    0.06
    =config
    0.06
    Act Density 0.115%

    No Known Activations