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

    Neuronpedia

    INDEX
    Explanations

    various languages and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಗೊಳ್ಳ
    1.19
    nrow
    1.19
    sion
    1.17
     ім
    1.17
     Webseite
    1.14
    菣
    1.12
    ಗೊಂಡ
    1.11
    ︹
    1.10
    aol
    1.10
     appetizing
    1.09
    POSITIVE LOGITS
    freund
    1.17
    сез
    1.01
    ਜ਼
    1.00
     nghề
    0.98
    alling
    0.96
    Clothing
    0.96
     personalisation
    0.96
     luxe
    0.96
    apers
    0.94
    璿
    0.94
    Act Density 0.004%

    No Known Activations