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

    Neuronpedia

    INDEX
    Explanations

    initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KeepOriginal
    0.39
    евна
    0.38
     दूरी
    0.38
     সরাসরি
    0.37
    ovaná
    0.36
     ঢেউ
    0.35
     draft
    0.35
    截止
    0.35
    tcpHeader
    0.35
     recid
    0.34
    POSITIVE LOGITS
     initialization
    1.63
     Initialization
    1.52
     initialize
    1.51
    初始化
    1.51
    Initialization
    1.50
     initializes
    1.50
     initializing
    1.49
     Initialize
    1.48
     初始化
    1.48
    Initialize
    1.42
    Act Density 0.042%

    No Known Activations