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

    Neuronpedia

    INDEX
    Explanations

    self initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㷫
    0.46
    人が
    0.42
     ಮೂಲಕ
    0.40
    উৎ
    0.40
     পাবে
    0.40
    ደም
    0.40
    Για
    0.39
    STOCK
    0.39
     vaisse
    0.39
    drill
    0.39
    POSITIVE LOGITS
    this
    0.54
     constructor
    0.53
     initialize
    0.50
     {}
    0.50
    constructor
    0.49
     конструк
    0.49
    构造
    0.49
     these
    0.48
     initializer
    0.48
    these
    0.48
    Act Density 0.037%

    No Known Activations