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

    Neuronpedia

    INDEX
    Explanations

    understand meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odoc
    0.71
    frastructure
    0.67
     facil
    0.66
     pipelines
    0.65
     checkBox
    0.65
    estep
    0.64
    搅拌
    0.64
     نموذج
    0.63
     Quels
    0.63
     نموذ
    0.63
    POSITIVE LOGITS
     meaning
    3.85
     meanings
    3.51
    meaning
    3.23
     Meaning
    3.21
    Meaning
    3.15
    含义
    3.11
     significado
    3.10
     significato
    3.00
     의미
    2.99
    意味
    2.75
    Act Density 1.641%

    No Known Activations