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

    Neuronpedia

    INDEX
    Explanations

    Executive Summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obfusc
    0.37
     layered
    0.36
     tangled
    0.34
     diagrams
    0.33
     denoted
    0.33
     figured
    0.32
     objects
    0.32
     particles
    0.31
     meshes
    0.31
     partly
    0.31
    POSITIVE LOGITS
     Synopsis
    0.52
    概要
    0.47
     Overview
    0.46
    BESCHREIBUNG
    0.46
    简介
    0.46
     Características
    0.46
     descripción
    0.45
    概述
    0.43
     descrição
    0.43
     Description
    0.43
    Act Density 0.001%

    No Known Activations