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

    Neuronpedia

    INDEX
    Explanations

    travel plans, duration, and value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ी
    1.91
    ity
    1.71
     totality
    1.62
    𝑎
    1.56
     tranche
    1.56
     tangible
    1.55
    ામ
    1.54
    𝑟
    1.51
     tact
    1.49
    pluck
    1.47
    POSITIVE LOGITS
    騨
    1.72
    convex
    1.65
     طے
    1.59
    ँग
    1.55
    ﻖ
    1.52
    gv
    1.51
    లో
    1.47
    াপন্ন
    1.47
    кә
    1.45
    ब्रेरी
    1.45
    Act Density 0.099%

    No Known Activations