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

    Neuronpedia

    INDEX
    Explanations

    how something is reflected or manifests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     possibilities
    0.41
     সম্ভাব
    0.38
    (',
    0.36
    resizable
    0.36
     depender
    0.36
    arp
    0.36
    ipe
    0.35
    utin
    0.35
     depends
    0.34
    ethylene
    0.34
    POSITIVE LOGITS
     reflected
    1.52
     manifested
    1.48
    reflected
    1.33
     manifests
    1.26
     manifest
    1.18
     проявля
    1.17
     manifesting
    1.10
     embodied
    1.07
     expressed
    1.03
    manifest
    0.99
    Act Density 0.039%

    No Known Activations