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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purity
    -0.07
    .show
    -0.06
     subtree
    -0.06
     послуг
    -0.06
    (home
    -0.06
     بند
    -0.06
     chef
    -0.06
     zenith
    -0.06
    وروب
    -0.06
    없음
    -0.06
    POSITIVE LOGITS
    ャ
    0.06
    gsub
    0.06
     APPLE
    0.06
     �
    0.06
     mềm
    0.06
    Apple
    0.06
    FAILED
    0.06
     thirds
    0.06
    写
    0.06
    idd
    0.06
    Act Density 0.003%

    No Known Activations