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

    Neuronpedia

    INDEX
    Explanations

    bun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gracious
    -0.07
     apar
    -0.06
    avra
    -0.06
     sak
    -0.06
     Cabinets
    -0.06
    <location
    -0.06
    ์ค
    -0.06
     cortisol
    -0.06
     Houston
    -0.06
    -fw
    -0.06
    POSITIVE LOGITS
    orpion
    0.07
    ızı
    0.07
     UN
    0.06
    =num
    0.06
     Bermuda
    0.06
    Trim
    0.06
    .',↵
    0.06
    Пер
    0.06
     طبق
    0.06
    .handleChange
    0.06
    Act Density 0.000%

    No Known Activations