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

    Neuronpedia

    INDEX
    Explanations

    iterative or IT related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可以说是
    1.23
     brainchild
    1.15
    可以
    1.15
     astute
    1.09
    いる
    1.08
    可以将
    1.08
    hair
    1.07
    hx
    1.05
     adept
    1.04
     tributary
    1.04
    POSITIVE LOGITS
    inerary
    1.52
    ligo
    1.43
    р
    1.37
    uitary
    1.24
    ল
    1.24
    llo
    1.22
    il
    1.21
    uraea
    1.21
    зации
    1.21
    倆
    1.20
    Act Density 0.174%

    No Known Activations