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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /stats
    -0.06
     سفر
    -0.06
    话
    -0.06
    的事
    -0.06
    _transactions
    -0.06
     نمونه
    -0.06
     Like
    -0.06
    ้อย
    -0.06
    /min
    -0.05
    話
    -0.05
    POSITIVE LOGITS
     bajo
    0.07
    oods
    0.07
    Virtual
    0.06
    Use
    0.06
    aroo
    0.06
    orea
    0.06
    итай
    0.06
    _boost
    0.06
    .touch
    0.06
    =current
    0.06
    Act Density 0.001%

    No Known Activations