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

    Neuronpedia

    INDEX
    Explanations

    code, programming, script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রুশ
    0.83
    糈
    0.69
     buruk
    0.68
     russo
    0.68
     expensive
    0.68
     அறிய
    0.67
     Astrophysics
    0.67
     thirds
    0.67
     effettuare
    0.67
    ッシング
    0.67
    POSITIVE LOGITS
    Bro
    0.65
    rive
    0.63
     ਪਰ
    0.62
    impl
    0.62
    Implement
    0.61
    èn
    0.60
    வீ
    0.60
     Glen
    0.59
    oba
    0.59
    آپ
    0.59
    Act Density 0.066%

    No Known Activations