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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     서비스
    -0.07
    cala
    -0.06
     Pillow
    -0.06
     Surrey
    -0.06
     Cous
    -0.06
    Northern
    -0.06
     Bust
    -0.06
     destinations
    -0.06
     Special
    -0.06
    OST
    -0.06
    POSITIVE LOGITS
    .／
    0.07
    956
    0.06
     walkers
    0.06
    755
    0.06
    ',$
    0.06
     будь
    0.06
    students
    0.06
    \Template
    0.06
    Î
    0.06
    ל
    0.06
    Act Density 0.069%

    No Known Activations