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

    Neuronpedia

    INDEX
    Explanations

    't

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    获批
    -0.08
    嗵
    -0.08
    柠檬
    -0.07
     Brittany
    -0.07
     들어
    -0.07
    🏺
    -0.07
     HCI
    -0.07
    奢侈品
    -0.07
     sublicense
    -0.07
    都认为
    -0.07
    POSITIVE LOGITS
     Watts
    0.08
    _SF
    0.07
    cul
    0.07
     bending
    0.07
    罩
    0.07
    ounters
    0.07
     letterSpacing
    0.07
    pir
    0.07
    Talk
    0.07
    -operation
    0.07
    Act Density 0.026%

    No Known Activations