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

    Neuronpedia

    INDEX
    Explanations

    it's about what something refers to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    1.38
     appellant
    1.10
    ل
    1.06
     ১০০
    1.05
    inine
    1.03
    द्व
    1.01
     sunny
    0.98
     appellants
    0.97
     unsuspecting
    0.96
    рија
    0.96
    POSITIVE LOGITS
    i
    1.42
     również
    1.30
    ে
    1.20
    将
    1.17
    Image
    1.16
    Data
    1.16
    Edge
    1.16
    es
    1.13
    Type
    1.13
    el
    1.13
    Act Density 0.185%

    No Known Activations