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

    Neuronpedia

    INDEX
    Explanations

    urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    index
    1.00
    Index
    0.89
    Office
    0.86
    introduction
    0.84
    Introduction
    0.84
    README
    0.82
    Overview
    0.81
    detail
    0.81
    Category
    0.81
    office
    0.79
    POSITIVE LOGITS
     이름을
    0.97
     부여
    0.94
     paranoia
    0.94
    َر
    0.94
     방식
    0.92
     Diffusion
    0.90
    轱
    0.89
     축
    0.89
    sthresh
    0.88
    팅
    0.88
    Act Density 0.042%

    No Known Activations