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

    Neuronpedia

    INDEX
    Explanations

    advertisements, user interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Soldiers
    -0.07
    obierno
    -0.07
    Pod
    -0.07
     appealed
    -0.06
    咖
    -0.06
    展
    -0.06
    )}}"
    -0.06
    ואה
    -0.06
    とても
    -0.06
    qué
    -0.06
    POSITIVE LOGITS
     shortly
    0.07
     남
    0.07
     Derek
    0.07
    潴
    0.07
     Dickinson
    0.07
    丰满
    0.07
     Dion
    0.07
    避孕
    0.07
     envision
    0.06
     اﻷ
    0.06
    Act Density 0.014%

    No Known Activations