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

    Neuronpedia

    INDEX
    Explanations

    all-around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     too
    0.39
    orant
    0.39
    ged
    0.38
    lea
    0.37
    cd
    0.37
    shed
    0.37
     Shed
    0.36
    atini
    0.36
    复杂的
    0.35
     ged
    0.35
    POSITIVE LOGITS
     round
    0.63
    整體
    0.60
     overall
    0.57
    round
    0.57
    Overall
    0.57
    overall
    0.56
    总体
    0.54
    整体
    0.52
    方面
    0.52
     ROUND
    0.52
    Act Density 0.004%

    No Known Activations