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

    Neuronpedia

    INDEX
    Explanations

    selectors and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.48
    isticated
    0.48
    ed
    0.43
    x
    0.42
    ilte
    0.40
    ت
    0.40
     nessa
    0.39
    buje
    0.39
    ხედ
    0.39
    Mode
    0.38
    POSITIVE LOGITS
     ተጨማሪ
    0.46
    ضاف
    0.46
     добав
    0.46
     Ajoutez
    0.45
     Dublin
    0.45
     ấn
    0.44
     Zentrum
    0.44
    íoch
    0.44
    addData
    0.43
     novità
    0.43
    Act Density 0.003%

    No Known Activations