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

    Neuronpedia

    INDEX
    Explanations

    privacy and data access limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mycobacterium
    0.50
     archaeologist
    0.47
     anyag
    0.46
     archaeology
    0.46
     archaeologists
    0.45
     arke
    0.44
     Archae
    0.43
    getTargetContext
    0.43
     glLight
    0.43
    চক
    0.43
    POSITIVE LOGITS
    Data
    0.52
    Dec
    0.48
    Decode
    0.48
    Privacy
    0.47
    Ben
    0.46
    B
    0.46
    AI
    0.46
    Be
    0.45
    Proxy
    0.44
    SDK
    0.44
    Act Density 0.002%

    No Known Activations