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

    Neuronpedia

    INDEX
    Explanations

    research methodology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াত
    1.07
    으면
    1.07
    arbe
    1.07
    гом
    1.05
    ങ്ങളും
    1.05
     станов
    1.03
    നില്‍
    1.02
     качестве
    1.01
    攘
    0.99
    뜹
    0.99
    POSITIVE LOGITS
    س
    1.44
    Pinterest
    1.05
    к
    1.00
     छीन
    0.99
    ंधर
    0.98
    e
    0.98
     পড়েন
    0.97
    εκ
    0.95
     chargeable
    0.95
     पॉजिटिव
    0.95
    Act Density 0.000%

    No Known Activations