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

    Neuronpedia

    INDEX
    Explanations

    technical and descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bipartisan
    0.55
    که
    0.50
    lama
    0.49
     musicale
    0.47
     чыныгы
    0.47
     ALE
    0.46
     거짓
    0.45
     ปก
    0.44
    ্নান
    0.44
     amulet
    0.44
    POSITIVE LOGITS
    Preference
    0.47
    ának
    0.46
    لي
    0.46
    Bee
    0.46
    推进
    0.46
    出现
    0.45
    Frank
    0.44
    áni
    0.44
    ле
    0.42
     المثال
    0.42
    Act Density 0.000%

    No Known Activations