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

    Neuronpedia

    INDEX
    Explanations

    dependency and derivation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fowl
    0.43
     مل
    0.41
     plunge
    0.38
    حول
    0.38
     swans
    0.37
     meter
    0.36
     motel
    0.36
    暈
    0.36
     Server
    0.36
     قريب
    0.36
    POSITIVE LOGITS
     dependencies
    0.91
     dependency
    0.88
    dependency
    0.79
    Dependencies
    0.78
     Dependency
    0.77
     Dependencies
    0.77
    Dependency
    0.76
    dependencies
    0.72
    任务
    0.72
    依赖
    0.71
    Act Density 0.014%

    No Known Activations