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

    Neuronpedia

    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    st
    0.47
    回應
    0.45
    "]["
    0.44
     できる
    0.44
    inv
    0.43
    map
    0.43
     mind
    0.42
    syntax
    0.42
    応答
    0.42
     ഇമാ
    0.42
    POSITIVE LOGITS
    oyant
    0.57
    ﻒ
    0.45
     Sod
    0.44
    жается
    0.44
    ்த்து
    0.43
     تصوی
    0.43
     JMJD
    0.43
    চা
    0.42
     отдела
    0.42
     cadast
    0.42
    Act Density 0.001%

    No Known Activations