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

    Neuronpedia

    INDEX
    Explanations

    Tool

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tbl
    -0.07
    빌
    -0.06
    Collider
    -0.06
     convers
    -0.06
    ソン
    -0.06
     assault
    -0.06
    ým
    -0.06
     multimedia
    -0.06
    -0.06
    -T
    -0.06
    POSITIVE LOGITS
    burse
    0.07
    celed
    0.07
    么
    0.06
    roi
    0.06
     Dow
    0.06
     QLatin
    0.06
     круп
    0.06
     civilizations
    0.06
    Else
    0.06
    ribbon
    0.06
    Act Density 0.001%

    No Known Activations