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

    Neuronpedia

    INDEX
    Explanations

    swift language code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    变
    0.46
     var
    0.45
     biến
    0.43
     VAR
    0.41
    ঙ্গের
    0.41
     변
    0.40
    var
    0.40
    変
    0.40
    емов
    0.39
     வைத்த
    0.39
    POSITIVE LOGITS
     extension
    0.49
    whal
    0.44
     extensions
    0.41
    EXTENSION
    0.41
    extension
    0.41
     playerId
    0.38
     extensión
    0.38
     print
    0.37
    Extension
    0.36
     protocolo
    0.36
    Act Density 0.003%

    No Known Activations