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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setObject
    -0.07
     PREFIX
    -0.07
    見
    -0.07
     dầu
    -0.06
    速
    -0.06
    Sum
    -0.06
     importantes
    -0.06
     am
    -0.06
     sớm
    -0.06
    _py
    -0.06
    POSITIVE LOGITS
     dispenser
    0.09
     Straw
    0.06
     jov
    0.06
     Practice
    0.06
     โ
    0.06
    _configs
    0.06
    _quiz
    0.06
    ]').
    0.06
     Employer
    0.06
    ................................
    0.06
    Act Density 0.047%

    No Known Activations