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

    Neuronpedia

    INDEX
    Explanations

    Code and configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ：“
    -0.07
    191
    -0.07
     annoy
    -0.07
     governments
    -0.07
     complaint
    -0.06
     Jahres
    -0.06
    Engineering
    -0.06
     heute
    -0.06
     Halloween
    -0.06
     бак
    -0.06
    POSITIVE LOGITS
    .Misc
    0.07
     проек
    0.06
     dung
    0.06
     général
    0.06
     Sergeant
    0.06
    metric
    0.06
    Introduction
    0.06
     라이
    0.06
    emsp
    0.06
    يع
    0.06
    Act Density 0.003%

    No Known Activations