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

    Neuronpedia

    INDEX
    Explanations

    building, construction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tc
    -0.07
    еты
    -0.07
     yn
    -0.07
    Triangle
    -0.07
     Directorate
    -0.06
    카
    -0.06
     Presidential
    -0.06
     у
    -0.06
     Mafia
    -0.06
     Een
    -0.06
    POSITIVE LOGITS
     Blond
    0.07
    _EDIT
    0.07
     inflamm
    0.06
     крем
    0.06
    _cliente
    0.06
     condos
    0.06
     یوتی
    0.06
     Singap
    0.06
     einmal
    0.06
    IFT
    0.06
    Act Density 0.039%

    No Known Activations