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

    Neuronpedia

    INDEX
    Explanations

    delete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     집
    -0.07
     BaseType
    -0.07
    ắ
    -0.07
     absolute
    -0.07
    냏
    -0.07
     NDEBUG
    -0.07
    .converter
    -0.07
     nelle
    -0.07
     BER
    -0.07
     ödül
    -0.06
    POSITIVE LOGITS
    爱
    0.07
     AVG
    0.07
    paid
    0.07
     cords
    0.07
    \\\
    0.07
     rolling
    0.07
    _LA
    0.07
    Rad
    0.06
    狎
    0.06
     fixing
    0.06
    Act Density 0.001%

    No Known Activations