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

    Neuronpedia

    INDEX
    Explanations

    memory bytes and address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cucumber
    0.97
     Anushka
    0.92
     cosmetology
    0.90
     cucumbers
    0.89
     fondant
    0.87
     ಸಿನಿ
    0.86
     कारवाई
    0.85
     renovation
    0.84
     toJson
    0.84
     Catholicism
    0.84
    POSITIVE LOGITS
     memory
    1.65
     pointer
    1.62
     address
    1.48
    地址
    1.44
     bytes
    1.44
     pointers
    1.43
    内存
    1.41
    Memory
    1.40
     Memory
    1.40
     byte
    1.39
    Act Density 0.604%

    No Known Activations