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

    Neuronpedia

    INDEX
    Explanations

    [noun/adjective] [preposition/descriptor]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लहान
    0.40
    멍
    0.38
    愣
    0.38
    JPG
    0.37
     gallant
    0.37
    皖
    0.36
     फोर्स
    0.36
     diner
    0.35
    鸾
    0.35
     contempl
    0.35
    POSITIVE LOGITS
    esModule
    0.44
    alkoz
    0.40
     Cord
    0.39
     Prabhu
    0.38
    allclasses
    0.38
     enchantment
    0.38
    在日本
    0.37
     TypeScript
    0.37
     Generated
    0.37
     dataType
    0.37
    Act Density 0.000%

    No Known Activations