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

    Neuronpedia

    INDEX
    Explanations

    nil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     النواب
    -0.08
     Laurent
    -0.08
    -rock
    -0.07
     Park
    -0.07
     добав
    -0.07
     KK
    -0.06
     Oklahoma
    -0.06
     судебн
    -0.06
    ("/
    -0.06
    肇庆
    -0.06
    POSITIVE LOGITS
     quello
    0.07
    _CODES
    0.07
     volunt
    0.07
    (service
    0.07
    IED
    0.06
    厕
    0.06
    ]=(
    0.06
    _preference
    0.06
    碘
    0.06
    ɫ
    0.06
    Act Density 0.005%

    No Known Activations