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

    Neuronpedia

    INDEX
    Explanations

    introduction or overview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ákat
    0.42
    usehen
    0.35
    enhuma
    0.34
     tenido
    0.33
    endrá
    0.33
    ilmente
    0.32
    ialmente
    0.32
    transfected
    0.32
    0.32
    ⬝
    0.32
    POSITIVE LOGITS
    Introduction
    0.57
    Overview
    0.55
     Introduction
    0.54
     Overview
    0.54
     overview
    0.49
     About
    0.47
     Summary
    0.46
    About
    0.45
    Background
    0.45
    Summary
    0.45
    Act Density 4.132%

    No Known Activations