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

    Neuronpedia

    INDEX
    Explanations

    compile and run

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     postpaid
    0.39
     absorbers
    0.38
     resorption
    0.38
     होश
    0.37
     dãy
    0.37
     государство
    0.36
     टिका
    0.36
     δεδο
    0.36
    兼用
    0.35
     multivalued
    0.35
    POSITIVE LOGITS
    编译
    1.48
    运行
    1.42
     run
    1.38
     compile
    1.38
    Run
    1.32
    run
    1.27
     compiling
    1.26
     Run
    1.23
    Compile
    1.22
     Compile
    1.20
    Act Density 0.065%

    No Known Activations