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

    Neuronpedia

    INDEX
    Explanations

    yes or no classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🚤
    1.43
    🎺
    1.39
    🛳
    1.38
    👪
    1.37
    📛
    1.35
    🗾
    1.35
    🦒
    1.34
    ⚓
    1.34
    🐡
    1.33
    🏝
    1.33
    POSITIVE LOGITS
    umen
    1.07
    웁
    1.05
     καλ
    0.98
    hees
    0.97
    ikov
    0.94
    του
    0.93
    ym
    0.92
    omey
    0.92
    oyle
    0.87
    ίου
    0.86
    Act Density 0.019%

    No Known Activations